# RoadMap Technologies — Complete Knowledge Base (/llms-full.txt)

> RoadMap Technologies is a forecasting and data science company offering expert consulting, enterprise forecasting software, and secure data services, built on the Geneva Forecasting™ Engine that Oracle has licensed since 1999.

> Summary index: https://roadmap-tech.com/llms.txt · Canonical site: https://roadmap-tech.com/

## Company Overview

- **Legal name:** RoadMap Technologies, Inc.
- **Founded:** 1988 by Rudolph Pizzano III, Ph.D. (Founder, President & CEO, Harvard Business School)
- **Headquarters:** 100 Cummings Center, Beverly, MA 01915, US
- **Contact:** info@roadmap-tech.com · (978) 232-8901 · https://roadmap-tech.com/contact/
- **Mission:** Help mission-critical teams forecast, plan, and act with precision through expert consulting, enterprise forecasting software, and secure data systems.
- **Engagement model:** Start small. Show dollars. Expand. (A governed demand model running on your data in about 2 weeks; most clients see measurable results within 30 days.)
- **Key proof points:** Forecasting since: 1988 · Saved for clients: $100M+ · Top life science companies served: 10 of 25 · Inside Oracle: 25+ yrs
- **Industries served:** Life Sciences, Healthcare, Retail & Consumer Goods, Consumer Electronics, Media & Entertainment, Energy & Utilities, Manufacturing, Finance, Government & Defense
- **Core values:** Privacy (Sensitive data is handled with security in mind from the first conversation.) Integrity (We report the numbers as they are, including when a model is not the answer.) Sustainability (Planning that reduces waste: less overstock, fewer emergency orders.) Timeliness (Models that ship in weeks, on the cadence your planning cycle runs.) Collaboration (We work alongside your planners, analysts and leadership, not around them.) Continuous learning (Four decades of forecasting research, and still testing what works.)
- **Official links:** [TrailBlazer Web App](https://app.roadmap-tech.com/TrailBlazer) · [Geneva Developer Portal](https://portal.roadmap-tech.com) · [API Docs](https://portal.roadmap-tech.com/docs) · [Python SDK on PyPI](https://pypi.org/project/geneva-forecast/) · [MCP Server on PyPI](https://pypi.org/project/geneva-mcp/) · [GitHub](https://github.com/RoadMap-Tech) · [LinkedIn](https://www.linkedin.com/company/roadmap-technologies/)

### General Frequently Asked Questions

- **What does RoadMap Technologies do?** RoadMap Technologies is a forecasting and data science company founded in 1988. We offer consulting services, forecasting software and data services, all built on the Geneva Forecasting™ Engine, the statistical engine Oracle has licensed since 1999.
- **What is the Geneva Forecasting™ Engine?** Geneva is an expert-system forecasting engine. For each time series it tests 10 statistical methods, tunes their parameters, detects seasonality and outliers, and selects the best fit. Oracle has licensed it since 1999, and it still ships inside Oracle Database 26 OLAP DML.
- **Which industries do you work with?** Life sciences, healthcare, retail and consumer goods, consumer electronics, media and entertainment, energy and utilities, manufacturing, finance, and government and defense. We have supported Fortune 500 companies and 10 of the Top 25 life science companies.
- **How fast can we get started?** Most engagements start with a pilot. We typically have a governed demand model running on your data in about two weeks, and most clients see measurable results within 30 days.
- **Do I need software or consulting?** If your team wants to run forecasts themselves, start with TrailBlazer or the Geneva API. If you need help building, validating and operationalizing models, or connecting them to S&OP, start with consulting. Many clients use both, and we can help you choose.

---

## Geneva Forecasting™ Engine

URL: https://roadmap-tech.com/geneva-forecasting-engine/

The Geneva Forecasting™ Engine is the rule-based C++ statistical expert system behind RoadMap's software and consulting, and the forecasting engine Oracle has licensed since September 1999. Born out of econometric research by Rudolph Pizzano III, Ph.D. at Harvard Business School in the 1980s, it served as the statistical core of Oracle OLAP, Oracle Demand Planning, and Oracle Retail Forecasting, and still ships today inside Oracle Database 26 OLAP DML.

### Engine Specifications
- **Average latency:** < 200 ms (per forecast via the API)
- **Throughput:** 1,500+/s (forecasts on enterprise deployments)
- **Hardware:** CPU-only (optimized C++, no GPUs)
- **Granularity:** 15-min → annual (sub-hourly to long-range planning)

### The 10 Statistical Methods

| # | Method | UI Label | Family | Model Form | Best For | Summary |
|---|---|---|---|---|---|---|
| 1 | Linear regression | Linear Regression | Regression | `y = a·x + b` | Steady linear trend | Fits a straight-line trend through time. The baseline every other method has to beat. |
| 2 | Power regression | Non-Linear Regression (Type 1) | Regression | `y = c·xᵃ` | Growth that accelerates or decelerates proportionally | Captures growth whose rate scales with time, curving up or flattening depending on the exponent. |
| 3 | Exponential regression | Non-Linear Regression (Type 2) | Regression | `y = c·eᵃˣ` | Compounding growth or decay (e.g. aging products) | Models a constant percentage change per period: compounding growth, or steady decay for aging products. |
| 4 | Logarithmic regression | Non-Linear Regression (Type 3) | Regression | `y = a·ln(x) + b` | Fast early growth that flattens | Rises quickly at first, then levels off. Typical of adoption that saturates gradually. |
| 5 | Asymptotic regression | Non-Linear Regression (Type 4) | Regression | `y = x / (a + b·x)` | Growth approaching a ceiling | Approaches a fixed upper limit, useful when capacity or market size caps demand. |
| 6 | Exponential asymptotic (logistic / S-curve) regression | Non-Linear Regression (Type 5) | Regression | `y = cKeᵃˣ / (1 + ceᵃˣ)` | Product launches and market saturation | The S-curve: slow start, rapid adoption, then saturation. The classic shape of a product launch. |
| 7 | Single exponential smoothing | Single Exponential Smoothing | Exponential smoothing | `Weighted average of past values` | Short-term, non-seasonal data | Weights recent observations more heavily than older ones. Fast and robust for short horizons. |
| 8 | Double exponential smoothing (Holt's linear trend) | Double Exponential Smoothing | Exponential smoothing | `Smoothed level + trend` | Trending, non-seasonal data | Adds a smoothed trend term to the level, so forecasts follow a series that is rising or falling. |
| 9 | Holt-Winters (triple exponential smoothing) | Holt-Winters | Exponential smoothing | `Level + damped trend + multiplicative seasonality` | Seasonal data | Smooths level, a damped trend, and a multiplicative seasonal pattern together. The workhorse for seasonal demand. |
| 10 | Croston's method | Croston | Intermittent demand | `Separate smoothing of demand size and interval` | Intermittent / sparse demand (spare parts, slow movers) | Forecasts how much and how often separately, for items that sell in irregular bursts with many zero periods. |

### Official Oracle Documentation Citations
- [Oracle Demand Planning Implementation and User’s Guide, Release 12.1](https://docs.oracle.com/cd/E18727-01/doc.121/e13634/T295435T478846.htm)
- [Oracle OLAP Application Developer’s Guide 10g Release 1](https://docs.oracle.com/cd/B13789_01/olap.101/b10333/forecast.htm)
- [Oracle9i OLAP User’s Guide Release 2](https://docs.oracle.com/cd/B10500_01/olap.920/a95295/devdml3.htm)

### Geneva Engine FAQs

- **Is Geneva used by Oracle?** Yes. Oracle licensed the Geneva Forecasting™ Engine in 1999. It was the statistical core of Oracle OLAP, Oracle Demand Planning and Oracle Retail Forecasting, and it still ships inside Oracle Database 26 OLAP DML.
- **What forecasting methods does Geneva use?** Ten methods. Six regression forms (linear, power, exponential, logarithmic, asymptotic and logistic S-curve), single and double exponential smoothing, Holt-Winters, and Croston's method, plus automatic best-fit selection.
- **What is Croston's method?** Croston's method forecasts intermittent demand, meaning items that sell in irregular bursts with many zero periods. It smooths demand size and the interval between demands separately, which suits spare parts and slow movers.
- **Does Geneva need a GPU?** No. Geneva is a highly optimized C++ engine that runs on standard CPUs, averaging under 200 ms per forecast via the API.

---

## Forecasting Software Products

Hub URL: https://roadmap-tech.com/forecasting-software/

### RoadMap TrailBlazer (TrailBlazer)

- **URL:** https://roadmap-tech.com/forecasting-software/trailblazer/
- **Tagline:** AI forecasting workspace in the browser with 40+ models, an interactive spreadsheet, and plain-language AI agents for planning teams.
- **Platform / Pricing Note:** Web
- **Definition:** RoadMap TrailBlazer is web-based AI forecasting software that combines an Excel-compatible spreadsheet, an AI Import Agent, an AI Forecast Analyst, and 40+ forecasting algorithms across five paradigms. The Free plan includes the full platform and the Oracle-licensed Geneva Forecasting™ Engine, with Pro ($34.99/mo) and Max ($69.99/mo) plans that unlock statistical, machine learning, deep learning, and TimeGPT foundation models.
- **Target audience:** Planning and S&OP teams that live in spreadsheets today and want a free, zero-setup browser workspace; Analysts who need to benchmark statistical, machine learning, deep learning, and TimeGPT models side by side; Teams proving the ROI of automated best-fit forecasting on their own SKUs before an enterprise rollout

#### Key Features
- **40+ Forecasting Models:** Benchmark RoadMap Geneva, classical statistical, machine learning, deep learning, and TimeGPT foundation models side by side. Automatic model selection identifies the optimal fit for your data.
- **AI Forecast Analyst:** Ask questions about your forecast in plain language. Receive chart-aware explanations of trends, seasonal peaks, anomalies, and strategic recommendations.
- **AI Data Import Agent:** Upload any raw CSV and guide the ETL import with natural-language instructions, with optional AI code execution to normalize, filter, and structure large datasets automatically.
- **Interactive Spreadsheet:** Full Excel-function support directly in the browser. Manage dozens of SKUs, inspect each row's selected model, and edit or validate data with no export required.
- **Conformal Prediction & Event Monte Carlo:** Generate calibrated 80%, 90%, or 95% conformal prediction intervals and run Monte Carlo simulations for discrete events like promotions or loss of exclusivity.
- **Save, Share and Collaborate:** Persist forecasts to the cloud, share live spreadsheets with your team, and export native Excel workbooks or presentation-ready charts.

#### TrailBlazer Pricing Plans
- Note: Free forever with the Geneva Engine · Upgrade to Pro ($34.99/mo) or Max ($69.99/mo) for 40+ models
- **Free ($0):** Full workspace + RoadMap Geneva Forecasting™ Engine
- **Pro ($34.99/mo):** Unlocks Classical Statistical & Machine Learning models
- **Max ($69.99/mo):** Unlocks Deep Learning & TimeGPT Foundation models

#### TrailBlazer FAQs
- **What is included in the free version of TrailBlazer?** The Free plan ($0) is a permanent, full-featured workspace, not a time-limited trial. It includes the RoadMap Geneva Forecasting™ Engine (Geneva Expert, Linear and Non-Linear Regression I–V, Single and Double Exponential Smoothing, Holt-Winters, and Croston's), plus the AI Forecast Analyst, AI Import Agent, Interactive Spreadsheet, Conformal Prediction intervals, Automated Model Selection, and Excel/CSV import and export.
- **When should I upgrade to TrailBlazer Pro or Max?** Upgrade when you want to benchmark additional algorithm paradigms alongside Geneva. Pro ($34.99/month) unlocks 12 classical Statistical models (including Auto ARIMA, Auto ETS, Meta Prophet, and GARCH) and 11 Machine Learning models (including LightGBM, XGBoost RF, and Gaussian Process). Max ($69.99/month) adds 9 Deep Learning architectures (NHITS, NBEATS, LSTM, TCN, and more) and 6 TimeGPT Foundation Models (TimeGPT-1 through TimeGPT-2.1).
- **How does the AI Import Agent handle raw CSV or Excel files?** You can upload any raw CSV or spreadsheet without writing ETL scripts or reformatting columns by hand. The AI Import Agent automatically inspects your file, identifies date and value columns, normalizes time series formatting, and validates the data directly into the interactive spreadsheet grid.
- **What are conformal prediction intervals in TrailBlazer?** Conformal prediction generates statistically calibrated upper and lower bounds (such as 80%, 90%, or 95% confidence ranges) around your point forecast. Instead of relying on textbook normality assumptions that often fail on real-world SKUs, conformal intervals use actual holdout residuals so planners can see realistic upside and downside inventory risk.
- **Can we export forecasts back to Excel or presentations?** Yes. Every TrailBlazer plan lets you edit formulas directly in the browser spreadsheet, save live workspaces to the cloud to share with colleagues, export native Excel workbooks (.xlsx) and CSV files, and download high-resolution forecast charts for S&OP decks.

### Geneva Forecasting™ API & MCP (Geneva API)

- **URL:** https://roadmap-tech.com/forecasting-software/geneva-forecasting-api/
- **Tagline:** REST API, Python SDK, and MCP server access to the Oracle-licensed Geneva Forecasting™ Engine for developers and AI agents.
- **Platform / Pricing Note:** Web
- **Definition:** The Geneva Forecasting™ API gives developers direct access to the Geneva Forecasting™ Engine, the statistical engine Oracle has licensed since 1999. Send a time series and get back a forecast with prediction intervals, the selected method and fit metrics (MAPE, MAD and RMSE), in under 200 ms on average.
- **Target audience:** Developers adding forecasting to a product or internal tool; Data teams who need reliable baselines across thousands of series; AI agent builders who want Claude and other MCP clients to forecast directly; Enterprises that need on-premises deployment or data sovereignty

#### Key Features
- **10 methods, automatic selection:** The expert system tests regression, exponential smoothing, Holt-Winters and Croston against each series, tunes parameters, and returns the best fit. Or pick a method yourself.
- **Prediction intervals:** Set a confidence level and get calibrated upper and lower bounds for every forecast period.
- **Fit metrics on every call:** Each response includes the selected method plus MAPE, MAD and RMSE, so you can judge the forecast before you use it.
- **Batch forecasting:** Send many series in one request and get per-series results. Available on Developer and higher plans.
- **Python SDK:** `pip install geneva-forecast` gives you a typed client, batch helpers and built-in charting. Python 3.9+.
- **MCP server for AI agents:** `geneva-mcp` lets Claude and other MCP clients run forecasts in conversation and get back the numbers plus a chart.

#### Geneva Forecasting™ API Pricing Tiers
- **Free ($0/mo):** 1,000 forecasts / mo, 120 requests / min — No credit card, MCP access, All 10 methods + auto-select, No batch
- **Developer ($49.99/mo):** 100,000 forecasts / mo, 600 requests / min — Batch forecasting, Full API, MCP access, Prediction intervals
- **Business ($199.99/mo):** 1,000,000 forecasts / mo, High volume — Batch forecasting, Production workloads, Priority scale, MCP access
- **Enterprise (Custom):** Unlimited forecasts, Custom — Cloud or on-prem, Custom integration, Data sovereignty, Dedicated support

#### Geneva API FAQs
- **What is Geneva API?** The Geneva Forecasting™ API gives developers direct access to the Geneva Forecasting™ Engine, the statistical engine Oracle has licensed since 1999. Send a time series and get back a forecast with prediction intervals, the selected method and fit metrics (MAPE, MAD and RMSE), in under 200 ms on average.
- **How much does the Geneva Forecasting™ API cost?** The Free plan includes 1,000 forecasts a month with no credit card. Developer is $49.99 a month for 100,000 forecasts, Business is $199.99 a month for 1,000,000, and Enterprise is custom.
- **Which programming languages can I use?** Any language that can make an HTTPS request with JSON. There is an official Python SDK, geneva-forecast, and an MCP server, geneva-mcp, for AI agents.
- **Can Claude use the Geneva API?** Yes. Install the geneva-mcp server, add your API key to your Claude Desktop configuration, and Claude can run forecasts in conversation and get back the numbers and a chart.
- **How fast is the API?** Under 200 ms per forecast on average, and 1,500+ forecasts per second on enterprise deployments.
- **Does the API support batch forecasting?** Yes, on the Developer, Business and Enterprise plans. Send many series in one request and get typed per-series results.

### RoadMap GPS (RoadMap GPS)

- **URL:** https://roadmap-tech.com/forecasting-software/global-planning-solution/
- **Tagline:** Enterprise demand planning software combining the ease of Excel, the statistical power of R, and Microsoft SQL Server scalability.
- **Platform / Pricing Note:** Windows Desktop App
- **Definition:** RoadMap Global Planning Solution (RoadMap GPS) is a Windows desktop business planning and forecasting application that combines the ease of use of Excel, the statistical power of R, and the scalability of Microsoft SQL Server. Powered by the Geneva Forecasting™ Engine, it turns large datasets into decision-ready plans with governed workflows and OLAP reporting.
- **Target audience:** Planning teams that need one governed plan across demand, supply, finance, and operations; Analysts who want an Excel-style workflow backed by Microsoft SQL Server scalability

#### Key Features
- **Cross-functional planning workflows:** Connect forecasts to decisions and align demand, supply, finance, and operations around one version of the plan.
- **Governed templates and audit-friendly changes:** Standardize planning inputs with controlled templates while keeping history and accountability for updates.
- **KPIs, dashboards, and plan vs actual:** Use OLAP-style reporting to surface trends, track KPIs, and monitor performance against the plan.
- **Enterprise data scale:** Built to handle large datasets with SQL-backed scalability while keeping the experience familiar for spreadsheet users.

#### RoadMap GPS FAQs
- **What is RoadMap GPS?** RoadMap Global Planning Solution (RoadMap GPS) is a Windows desktop business planning and forecasting application that combines the ease of use of Excel, the statistical power of R, and the scalability of Microsoft SQL Server. Powered by the Geneva Forecasting™ Engine, it turns large datasets into decision-ready plans with governed workflows and OLAP reporting.
- **How does RoadMap GPS combine Excel usability with enterprise SQL Server scale?** Planners interact with familiar spreadsheet-style grids, formulas, and views on the Windows desktop while all historical actuals, statistical baselines, hierarchies, and overrides are stored and governed in a central Microsoft SQL Server database.
- **What is the difference between RoadMap GPS and RoadMap GPS 360?** RoadMap GPS focuses on cross-functional demand planning, Geneva statistical forecasting, OLAP reporting, and product lifecycle planning. RoadMap GPS 360 adds multi-market inventory tracking, international collaboration with version control, Management vs. Statistical vs. Monte Carlo scenario comparisons, and 360-degree executive BI rollups.
- **Which forecasting methods are included in RoadMap GPS?** RoadMap GPS embeds the Geneva Forecasting™ Engine—evaluating linear and non-linear regressions, exponential smoothing, Holt-Winters, and Croston's intermittent demand models with holdout accuracy metrics (MAD, MAPE, RMSE, Tracking Signal) and confidence intervals—alongside R-powered econometric and driver models.
- **Can RoadMap GPS connect to our ERP and corporate data warehouse?** Yes. RoadMap GPS integrates bi-directionally with SAP, Oracle, Microsoft Dynamics, Snowflake, and SQL Server environments to ingest shipment, order, and POS actuals and write approved consensus plans back to your operational systems.

### RoadMap GPS 360 (RoadMap GPS 360)

- **URL:** https://roadmap-tech.com/forecasting-software/gps-360/
- **Tagline:** Full-lifecycle planning software uniting best-fit forecasting, multi-market inventory tracking, and 360° executive visibility.
- **Platform / Pricing Note:** Windows Desktop App
- **Definition:** RoadMap GPS 360 is a Windows desktop enterprise planning and performance management platform that unifies Geneva best-fit forecasting, multi-market inventory tracking, international version control, and 360-degree executive business intelligence across brands, markets, and portfolios.
- **Target audience:** Global, multi-brand organizations that need performance management and executive visibility; Distributed commercial, supply, and finance teams planning across portfolios and hierarchies

#### Key Features
- **Inventory management across brands and markets:** Track inventory, ex-factory, and customer trends to keep stock levels aligned with real demand and supply chain realities.
- **International collaboration with version control:** Built for distributed teams working on portfolios and hierarchies, keeping stakeholders aligned and changes organized.
- **Decision-ready rollups from SKU to executive summaries:** Generate precise forecasts from individual items to total company views, helping leadership move quickly with confidence.
- **360° business intelligence + product lifecycle insights:** Unify forecasting, performance, and visibility with dashboards and notes that capture insights from launch through maturity.

#### RoadMap GPS 360 FAQs
- **What is RoadMap GPS 360?** RoadMap GPS 360 is a Windows desktop enterprise planning and performance management platform that unifies Geneva best-fit forecasting, multi-market inventory tracking, international version control, and 360-degree executive business intelligence across brands, markets, and portfolios.
- **What does RoadMap GPS 360 add on top of standard demand forecasting?** RoadMap GPS 360 adds a full-lifecycle performance management and executive visibility layer—uniting ex-factory shipments, channel inventory, and patient or customer cohorts with international version control, event calendars, and SKU-to-executive BI rollups.
- **How does scenario comparison work in RoadMap GPS 360?** Teams can build and compare Management, Statistical, and Monte Carlo scenarios side by side across therapy portfolios, brands, customer segments, and multi-year horizons to quantify financial and supply risk before locking the plan.
- **How does GPS 360 handle governance across distributed global teams?** Every assumption update, override, and version promotion is captured in a timestamped audit trail with user attribution and notes, allowing regional, brand, and corporate finance teams to collaborate without overwriting each other's plans.
- **Is RoadMap GPS 360 deployed on-premises or in a private cloud?** Both. RoadMap GPS 360 is a Windows desktop application backed by Microsoft SQL Server that can run entirely on-premises or inside your organization's private cloud VPC for strict data sovereignty.

### RoadMap StoreCast (StoreCast)

- **URL:** https://roadmap-tech.com/forecasting-software/storecast/
- **Tagline:** Shopify-native analytics and demand forecasting that turns order history into product and variant insights inside Shopify Admin.
- **Platform / Pricing Note:** Free Shopify App
- **Definition:** RoadMap StoreCast is a free, Shopify-native analytics and forecasting app that turns historical orders into clear product performance insights and lightweight demand forecasts without leaving Shopify Admin. With Shopify's Stocky app retired in 2026, StoreCast gives merchants product and variant views, seasonal demand projections, and one-click CSV exports for purchasing decisions.
- **Target audience:** Shopify merchants replacing Stocky who want native demand forecasting inside Shopify Admin; Ecommerce operators who track revenue, COGS, and variant velocity across spreadsheets today

#### Key Features
- **Sales + revenue clarity:** Visualize trends by product, variant, or store total, built for quick, repeatable inventory reviews.
- **Key metrics included:** Calculate revenue, cost of goods sold, and discounts to support inventory and purchasing decisions.
- **Demand forecasting:** Generate demand forecasts from historical sales with optional seasonality right inside Shopify Admin.
- **Export-friendly:** Export aggregated sales reports to CSV for deeper analysis in Google Sheets, Excel, or RoadMap TrailBlazer.

#### StoreCast FAQs
- **What is StoreCast?** RoadMap StoreCast is a free, Shopify-native analytics and forecasting app that turns historical orders into clear product performance insights and lightweight demand forecasts without leaving Shopify Admin. With Shopify's Stocky app retired in 2026, StoreCast gives merchants product and variant views, seasonal demand projections, and one-click CSV exports for purchasing decisions.
- **Is RoadMap StoreCast free for Shopify merchants?** Yes. StoreCast is a free Shopify app that installs directly from the Shopify App Store and runs inside your Shopify Admin.
- **Can I view sales and forecasts at both the product and variant level?** Yes. StoreCast lets you visualize historical trends and generate demand forecasts by total store, individual product, or specific variant, with optional seasonality.
- **Which financial and inventory metrics does StoreCast calculate?** Alongside unit sales and demand forecasts, StoreCast calculates revenue, cost of goods sold (COGS), and discounts so you can evaluate margin and purchasing priorities together.
- **Can I export StoreCast data to Excel or TrailBlazer?** Yes. StoreCast exports aggregated sales and forecast reports to CSV so you can open them directly in Excel, Google Sheets, BI tools, or RoadMap TrailBlazer for 40+ model benchmarking.

### PreSnap Picks (PreSnap Picks)

- **URL:** https://roadmap-tech.com/forecasting-software/presnap-picks/
- **Tagline:** Weekly NFL Moneyline, Spread, and Total predictions, scoring trend analysis, and a social Pick 'Em game powered by our models.
- **Platform / Pricing Note:** Free on iPhone
- **Definition:** PreSnap Picks is a free iPhone app from RoadMap Technologies that publishes weekly NFL game predictions, best bets, scoring trend analysis, and a social Pick 'Em game. It applies the same quantitative modeling discipline RoadMap uses for enterprise demand planning to pro football.
- **Target audience:** NFL fans who want a data-driven read on each week's games; Bettors who prefer model-based picks over hot takes; Anyone curious how forecasting models perform outside the boardroom

#### Key Features
- **NFL Predictions:** Weekly model projections across Moneyline, Spread, and Totals for every NFL game, tagged with Best Bet, Bet, and Low Value confidence tiers.
- **NFL Pick 'Em Game:** Lock in your weekly picks before kickoff and compete on Global and Friends leaderboards throughout the NFL season.
- **NFL Scoring Trends and Analysis:** Inspect 5-game scoring trajectories (Points For, Points Allowed, and Total) alongside historical head-to-head results for every matchup.
- **NFL News:** Follow trending and latest NFL stories, injury updates, and game previews filtered by your favorite team.

#### PreSnap Picks FAQs
- **What is PreSnap Picks?** PreSnap Picks is a free iPhone app from RoadMap Technologies that publishes weekly NFL game predictions, best bets, scoring trend analysis, and a social Pick 'Em game. It applies the same quantitative modeling discipline RoadMap uses for enterprise demand planning to pro football.
- **How does PreSnap Picks generate weekly NFL predictions?** Built by RoadMap's data science team, PreSnap Picks applies structured time-series and econometric modeling to team scoring trajectories, points allowed, pace, and matchup histories to project the Moneyline, Spread, and Over/Under Total for every NFL game each week.
- **What do the Best Bet, Bet, and Low Value badges mean?** Each projection is compared against the current market line to measure the statistical edge. Matchups where the model identifies the strongest probability advantage are tagged as Best Bet or Bet, while tight coin-flip lines are marked Low Value.
- **How does the weekly NFL Pick 'Em game work?** Users lock in their weekly game picks inside the app before kickoff and compete for accuracy on Global and Friends leaderboards throughout the NFL regular season and playoffs.
- **Is PreSnap Picks free to download?** Yes. PreSnap Picks is 100% free on the Apple App Store for iPhone, with no subscriptions or in-app purchases required to view predictions, scoring trends, NFL news, or play the Pick 'Em game.

---

## Consulting Services

Hub URL: https://roadmap-tech.com/consulting-services/

Forecasting experts who build, validate and operationalize demand models on your data.

### Econometric Modeling & Driver Analysis

- **URL:** https://roadmap-tech.com/consulting-services/econometric-modeling-driver-analysis/
- **Summary:** Patient behavior, market access, price, promotion. We isolate what's actually moving your demand, measure each driver, and turn it into decisions your commercial and planning teams can act on.
- **Definition:** Econometric modeling and driver analysis measures how patient behavior, market access, price, promotion and seasonality each move demand. RoadMap Technologies helps life science and consumer goods teams by building statistical models on their own data, from survival curves to elasticity models, so every forecast comes with the why behind the number.
- **Typical engagements:** Patient persistency and adherence from longitudinal data; Gross-to-net drivers across rebates, chargebacks and payer mix; Promotional lift and cannibalization by event and retailer; Price elasticity by product, channel or region

#### Life Sciences Applications
Brand volume is the product of patients starting, staying on therapy and getting reimbursed. We model each step from patient-level data so forecasts hold up in brand planning and finance review.
- **Patient persistency (Survival curves (Kaplan–Meier, Cox models)):** From longitudinal patient data (APLD), we estimate how long patients stay on therapy and which factors, such as line of therapy, payer or starting dose, shorten or extend it. *Outcome:* Forecast patients on therapy month by month and target where support programs extend duration.
- **Adherence and compliance (PDC, MPR and DACON):** Proportion of days covered, medication possession ratio, refill gaps and daily average consumption translate patient counts into realistic units by dose, strength and pack size, cohort by cohort. *Outcome:* Convert patients into units and revenue without assuming perfect compliance.
- **Gross-to-net drivers (Rebates, chargebacks, 340B and Medicaid):** We model how formulary position, Medicaid and 340B mix, chargebacks and contracted rebates turn gross sales into net revenue across retail, specialty and government channels. *Outcome:* Forecast the net revenue finance reports, not just gross demand.
- **Co-pay program impact (Co-pay cards, accumulators and abandonment):** We measure how co-pay cards and patient support change first-fill abandonment and refill rates, and how accumulator and maximizer programs shift out-of-pocket cost across the benefit year. *Outcome:* Size program budgets on the starts and refills they actually protect.
- **Market access effects (Formulary tier, prior authorization and step edits):** We quantify how formulary wins and losses, tier changes, prior authorization and step edits move new starts and approval rates, plan by plan and region by region. *Outcome:* Put a volume and revenue value on each contract and access decision.
- **Promotional response (HCP detailing, samples and carryover):** Response curves link calls, samples, speaker programs and non-personal promotion to new prescriptions by prescriber segment, with carryover, so you see where extra effort still pays and where it saturates. *Outcome:* Reallocate field and promotional spend toward the segments that still respond.

#### Consumer Goods & Retail Applications
Volume moves with price, promotion, distribution and the calendar, often all at once. We combine syndicated point-of-sale data with internal shipments and deal costs to separate each effect so commercial, revenue management and supply teams plan from the same numbers.
- **Promotional lift decomposition (Baseline vs. incremental volume on POS and shipments):** Combining NielsenIQ and Circana point-of-sale data with internal shipments and deal costs, we split each event's sales into baseline and incremental volume, net of the post-promotion dip and forward buying, so lift isn't overstated by pantry loading or retailer stocking. *Outcome:* See which events paid back their trade spend and which only shifted volume in time.
- **Price elasticity (Own- and cross-price elasticity):** Log-log demand models estimate how volume responds to price by SKU, channel and region, and where that volume goes when a competitor or sister product moves price. *Outcome:* Set list and promoted prices with a known volume trade-off.
- **Cannibalization and halo (Source of volume):** We measure how much of a promoted item's lift comes out of your own products, and which items pull related purchases along with them across the category. *Outcome:* Judge promotions on portfolio margin, not single-item volume.
- **Calendar and weather effects (Moving holidays, trading days and weather):** Shifting holidays such as Easter and Thanksgiving week, trading-day counts and weather are modeled separately from trend, so a late Easter isn't read as a demand problem. *Outcome:* Compare periods fairly and stop reacting to calendar noise.
- **Key-account profitability and matched-market tests (Retailer P&L simulation and test-vs.-control):** We model what a promotion or price change earns key retail accounts (such as Walmart, Costco, Kroger and Whole Foods) as well as the manufacturer, and design matched-market tests to prove incremental lift before rolling events out chain-wide. *Outcome:* Go into key-account negotiations with a calendar and P&L that work for both sides.
- **Marketing mix (Media ROI and adstock):** Marketing mix models separate the effect of TV, digital, retail media and trade spend on sales, with adstock carryover and diminishing returns, so each channel gets credit for the volume it drives. *Outcome:* Shift budget toward the channels with the highest incremental return.

#### Econometric Modeling & Driver Analysis FAQs
- **What is econometric modeling & driver analysis?** Econometric modeling and driver analysis measures how patient behavior, market access, price, promotion and seasonality each move demand. RoadMap Technologies helps life science and consumer goods teams by building statistical models on their own data, from survival curves to elasticity models, so every forecast comes with the why behind the number.
- **How do you measure price elasticity?** With demand models fitted to your sales history by SKU, channel and region, controlling for promotion, distribution, seasonality and competitor prices. The result is the percentage change in volume for a 1% change in price, plus where the lost or gained volume goes.
- **How is patient persistency modeled?** Persistency is how long patients stay on a therapy. We model it with survival curves, such as Kaplan–Meier and Cox models, fitted to anonymized patient-level data (APLD), and break it down by cohort, line of therapy, payer and starting dose.
- **What is DACON?** DACON is daily average consumption, the average number of units a patient uses per day, measured from prescription data. Combined with proportion of days covered and refill gaps, it converts patient counts into realistic units by dose and pack size.
- **How is promotional lift measured?** By estimating the baseline, meaning what would have sold without the promotion, and treating the rest as incremental volume. We net out the post-promotion dip, forward buying and cannibalization of your own products, so lift isn't overstated.

### Forecasting & Demand Planning

- **URL:** https://roadmap-tech.com/consulting-services/forecasting-demand-planning/
- **Summary:** Baselines, scenarios and forecast improvement built for real S&OP cycles in life sciences and consumer goods, with exception views and accuracy tracking your planners will actually use.
- **Definition:** Demand planning consulting is expert help building the statistical baselines, scenarios and accuracy tracking a planning team runs every S&OP cycle. RoadMap Technologies helps life science and consumer goods teams by putting a governed demand model on their data in about two weeks, using the Oracle-licensed Geneva Forecasting™ Engine, then proving the ROI before they scale.
- **Typical engagements:** Patient-based demand plans for oncology and specialty therapies; Improving forecast accuracy inside an existing S&OP process; Distribution requirements planning (DRP) and material requirements planning (MRP); Sales quota setting grounded in statistical baselines; Category growth forecasting; Expense planning and budgeting

#### Life Sciences Applications
Life science demand runs on patients, dosing and channels, not just shipment history. We build forecasts that brand, finance and supply teams can all work from, from the 0–24 month plan to the long-range view.
- **Patient-based demand (Patients → units by dose and pack):** We forecast patients on therapy from new starts and persistency, then convert them to units by dose, strength and pack size, so the plan reflects how the product is actually used. *Outcome:* Run patient-based S&OP that brand, finance and supply teams can each trace.
- **Specialty and oncology planning (Specialty pharmacy, buy-and-bill, weight-based dosing):** Specialty and oncology products move through specialty pharmacies, distributors and buy-and-bill accounts, with weight-based or cycle-based dosing. We model each channel and regimen separately, so specialty demand is not forced into a retail pattern. *Outcome:* Plan specialty demand by channel and regimen, not as one national number.
- **Sell-in vs. demand (852/867 data and wholesaler inventory):** Using 852 inventory and 867 sales-out data, we separate what wholesalers order from what patients and pharmacies consume, so stocking swings and buy-ins aren't mistaken for changes in underlying demand. *Outcome:* Forecast true demand and see channel inventory building before it unwinds.
- **Event-based forecasting (Label expansions, competitor entry, guideline changes):** We layer known and likely events onto the baseline, such as a new indication, a competitor launch or a treatment guideline update, each with its own timing, size and probability. *Outcome:* Show leadership exactly which events move the plan, and by how much.
- **Near-term to long-range plans (0–24 month demand linked to the 3–10 year plan):** We link the 0–24 month operational forecast to the 3–10 year long-range plan, so near-term demand, supply plans and LRP assumptions come from one model. *Outcome:* Keep the S&OP number and the long-range plan from drifting apart.
- **Accuracy and governance (MAPE, bias and forecast value added):** We score every brand, strength and channel forecast for error and bias each cycle, and set governance rules for who can change the number and when, so accuracy is reported, not assumed. *Outcome:* Hold the forecast process to a measured standard in every S&OP review.

#### Consumer Goods & Retail Applications
Thousands of SKUs, locations and channels, each with its own pattern. We give planners a statistical baseline for every series, scenarios for S&OP, and a clear view of where their time matters most.
- **Statistical baselines (Best-fit per series (Geneva)):** The Geneva engine tests ten statistical methods on every SKU, location and channel series, tunes them, detects seasonality and outliers, and keeps the best fit, with MAPE, MAD and RMSE reported. *Outcome:* Start every S&OP cycle from a tested baseline, not last year plus a percentage.
- **S&OP scenarios (Plan, upside and downside):** Plan, upside and downside scenarios share one baseline and one set of assumptions, so sales, finance and supply discuss the same numbers and the gap between them, not whose spreadsheet is right. *Outcome:* Agree on one demand plan faster, with the risks visible.
- **Short-horizon demand sensing (POS-driven adjustments):** For the next few weeks, we adjust the forecast with the latest point-of-sale and order data, so replenishment reacts to what shoppers are buying now rather than last month's plan. *Outcome:* Catch demand shifts in days, before they become stockouts or overstock.
- **Override tracking (Forecast value added (FVA)):** We measure whether each planner, sales or management override made the forecast better or worse than the statistical baseline, by product, customer and person, cycle after cycle. *Outcome:* Keep the overrides that add information and drop the ones that add bias.
- **Category growth forecasting (Category trends and 3–5 year volume):** We forecast category and segment growth from market data alongside your own sales, so share targets and the longer-range volume plan rest on a realistic view of where the market is heading. *Outcome:* Set share and volume targets against a category forecast, not a guess.
- **Quota and expense planning (Baselines for sales targets and budgets):** Statistical baselines by territory, account and product give sales quotas and expense budgets a defensible starting point, so targets reflect expected demand rather than last year's number plus a stretch. *Outcome:* Set quotas and budgets your sales and finance teams accept as fair.

#### Forecasting & Demand Planning FAQs
- **What is forecasting & demand planning?** Demand planning consulting is expert help building the statistical baselines, scenarios and accuracy tracking a planning team runs every S&OP cycle. RoadMap Technologies helps life science and consumer goods teams by putting a governed demand model on their data in about two weeks, using the Oracle-licensed Geneva Forecasting™ Engine, then proving the ROI before they scale.
- **How is pharma demand forecasting different from consumer goods forecasting?** Pharma demand is driven by patients rather than shoppers. Forecasts start from new starts, persistency and dosing, run through wholesaler, specialty pharmacy and buy-and-bill channels, and have to account for payer access, label events and gross-to-net. Consumer goods forecasts lean on SKU history, promotions and point-of-sale data.
- **How long does it take to get a forecast live?** We typically have a governed demand model running on your data in about two weeks. Most clients see measurable results within 30 days.
- **What data do you need to start?** Usually two or more years of sales or shipment history at the level you plan, plus any known drivers such as promotions or price changes. We can work from ERP extracts or spreadsheets.
- **How do you measure forecast accuracy?** Every series is scored with MAPE, MAD and RMSE against holdout periods before go-live, and against actuals every cycle after. Planner overrides are tracked separately so you can see which ones help.
- **Will this replace our planners?** No. The statistical baseline handles the routine series so planners can spend their time on exceptions, new products and the judgment calls that need people.

### Launch Forecasting

- **URL:** https://roadmap-tech.com/consulting-services/launch-forecasting/
- **Summary:** Forecasts for products with no sales history yet. We size the opportunity from patients or shoppers, shape the uptake from comparable launches, and track early results so the plan adjusts fast.
- **Definition:** Launch forecasting estimates demand for a new product before sales history exists. RoadMap Technologies helps life science and consumer goods teams by building patient-funnel and analog-based forecasts, fitting uptake curves to comparable launches, attaching risk ranges, and re-forecasting as early prescriptions or POS data arrive.
- **Typical engagements:** Patient-funnel forecasts for new brands and indications; Analog uptake and time to peak; New SKU and line-extension forecasts with cannibalization; Launch supply and channel-fill planning

#### Life Sciences Applications
A launch forecast sets supply, headcount and investment before the first prescription is written. Ours start from the patient funnel, shapes uptake on comparable brands, and sets the peak-year assumptions that feed the long-range plan.
- **Patient-funnel forecast (Epidemiology → diagnosed → treated → addressable):** We build demand from prevalence or incidence down through diagnosis, treatment and line of therapy to the addressable patients, then apply share, dosing and compliance to reach units and revenue. *Outcome:* Show every assumption behind peak sales, so brand, medical and finance can each challenge it.
- **Analog uptake (Normalized months from launch, time to peak):** We select comparable launches by indication, mechanism, order of entry and access, align them on months from launch, and use their curves to set time to peak and the shape of the ramp. *Outcome:* Ground the uptake curve in real launches rather than a hockey stick.
- **Diffusion and access ramp (Bass diffusion and payer coverage timing):** Bass diffusion models fitted to analog brands separate innovator from imitator adoption among prescribers, and we layer in when commercial, Medicare and Medicaid coverage actually starts, so the ramp reflects access. *Outcome:* Time the ramp to coverage decisions instead of assuming access on day one.
- **Launch risk ranges (Monte Carlo P10, P50 and P90):** We place distributions on peak share, time to peak, price and persistency, then simulate thousands of launches to show how wide the realistic range is and which assumptions drive it. *Outcome:* Give leadership and the long-range plan a range, with the biggest risks named.
- **Launch supply and channel fill (Initial stocking and launch safety stock):** We translate the launch curve into wholesaler and specialty pharmacy initial stocking, ongoing replenishment and launch safety stock, sized to the uncertainty in the forecast rather than a flat number of months. *Outcome:* Avoid launch stockouts without writing off short-dated product later.
- **Early-launch tracking (Weekly scripts against the launch curve):** As weekly prescription and claims data arrive, we compare new starts, refills and payer approvals against the curve, separate channel fill from real demand, and re-forecast the trajectory. *Outcome:* Spot an under-performing launch within weeks and adjust the plan fast.

#### Consumer Goods & Retail Applications
New items have no history, but they have relatives. We forecast them from comparable products, trial and repeat, and the distribution plan, then separate pipeline fill from what shoppers actually buy.
- **Analog and short-history models (Like-item S-curves and transfer learning):** We forecast new items from like-item histories and S-curves, and from TrailBlazer's transfer learning, which applies patterns learned across 47,000+ datasets to series with only a few weeks of data. *Outcome:* Get a credible forecast from week one instead of waiting for history.
- **Trial and repeat (Parfitt-Collins: trial × repeat × buying rate):** Volume is built from how many households try the product, how many come back, and how often they buy, so you can see whether growth depends on reach or on loyalty. *Outcome:* Tell a slow-trial launch from a weak-repeat one and fix the right problem.
- **Distribution build (ACV ramp by account):** We model how fast the item gains distribution by retailer and channel, using authorization dates and shelf reset timing, because most early volume follows weighted distribution, not consumer demand. *Outcome:* Plan volume around when shelves actually carry the item.
- **Pipeline fill vs. sell-through (Sell-in spike vs. consumer offtake):** Launch shipments include one-time pipeline fill for retailer DCs and shelves. We separate that spike from ongoing sell-through using POS data, so the run rate isn't overstated. *Outcome:* Avoid building production and inventory on a pipeline spike.
- **Source of volume (Cannibalization of the existing range):** We estimate how much of the new item's volume is incremental and how much comes from your existing products, by SKU and channel, so the launch is judged on net portfolio gain. *Outcome:* Size the incremental gain, not just the new item's gross volume.
- **Product transitions (Phase-in, phase-out and price compression):** For short-cycle categories such as consumer electronics, we plan the overlap between outgoing and incoming models and the price compression curve, using what happened in previous product generations. *Outcome:* Hand over between generations without stranded old stock or empty shelves.

#### Launch Forecasting FAQs
- **What is launch forecasting?** Launch forecasting estimates demand for a new product before sales history exists. RoadMap Technologies helps life science and consumer goods teams by building patient-funnel and analog-based forecasts, fitting uptake curves to comparable launches, attaching risk ranges, and re-forecasting as early prescriptions or POS data arrive.
- **How do you forecast a product with no sales history?** From the bottom up. For a medicine that means the patient funnel, from prevalence to treated patients, with share, dosing and persistency applied. For a consumer product it means trial, repeat and distribution. Comparable launches then set the shape and speed of the uptake curve.
- **How do you choose analog products?** We match on the factors that drive uptake, such as indication or category, mechanism or format, order of entry, price point, and access or distribution. We usually shortlist several analogs, align them on months from launch, and weight them by how closely they match.
- **How soon after launch can the forecast be updated?** Within weeks. We compare weekly prescription, claims or POS data against the launch curve, separate one-time channel fill from real demand, and re-forecast as soon as the trend is clear rather than waiting for the next quarterly cycle.
- **How do you plan launch inventory with so much uncertainty?** We size initial stocking and safety stock to the forecast range, not a single number. Monte Carlo ranges on the launch curve show the upside you need to cover and the downside where short-dated stock becomes a write-off risk.

### Supply Chain & Inventory Planning

- **URL:** https://roadmap-tech.com/consulting-services/supply-chain-inventory-planning/
- **Summary:** A forecast is only useful if it changes what you order. We connect demand to inventory policy, service levels and supply plans, from launch stock to long-range capacity, without overstocking.
- **Definition:** Supply chain and inventory planning links the demand forecast to what you actually make, stock and ship, through safety stock, service levels, replenishment and capacity. RoadMap Technologies helps life science and consumer goods teams by connecting statistical forecasts to inventory policy and supply plans, so stock protects service and margin without tying up cash.
- **Typical engagements:** Long-range supply and capacity plans; Collaborative planning, forecasting and replenishment (CPFR) with retail partners; Rightsizing safety stock across a distribution network; Forecasting spare parts and slow-moving items with Croston's method; Reducing stockouts during promotions

#### Life Sciences Applications
Pharma supply decisions are made months or years ahead, against shelf life, batch sizes and long lead times. We connect the demand forecast to channel inventory, safety stock and long-range capacity, with supply plans that run three to ten years out.
- **Channel inventory (Wholesaler weeks on hand, 852/867):** We track wholesaler and distributor weeks on hand from 852 and 867 data against fee-for-service and inventory management agreement limits, and plan shipments so channel stock stays within them. *Outcome:* Keep channel inventory inside agreed limits and avoid quarter-end loading.
- **Expiry-aware planning (Shelf life, FEFO and write-off risk):** We plan production and stock levels against remaining shelf life, first-expired-first-out rules and customer minimum dating, flagging lots at risk of expiry while there's still time to redeploy them. *Outcome:* Cut expiry write-offs without risking supply to patients.
- **Batch-aware safety stock (Campaign manufacturing and long lead times):** Safety stock and reorder points account for batch and campaign sizes, release testing time and long API and fill-finish lead times, rather than formulas that assume continuous production. *Outcome:* Hold the stock your manufacturing reality requires, and no more.
- **Allocation under constraint (Supply allocation rules during shortages):** When supply is short, we model allocation rules by customer, channel and market, testing how each option affects patients on therapy, contracts and revenue before the rules are applied. *Outcome:* Protect patients already on therapy and make shortage decisions you can defend.
- **Long-range supply and capacity (3–10 year supply plans):** We extend the demand forecast into 3–10 year supply plans covering API, drug product and packaging capacity, so manufacturing capacity and supplier commitments match the long-range plan. *Outcome:* Commit to capacity and supplier contracts years ahead with demand risk understood.
- **Specialty and cold-chain networks (Specialty pharmacy, distributors and limited distribution):** For specialty and cold-chain products in limited distribution networks, we plan inventory by specialty pharmacy and distributor, with shipping lanes, temperature control and small, high-value volumes built in. *Outcome:* Keep high-value product where patients need it, without excess sitting in the network.

#### Consumer Goods & Retail Applications
Every SKU and location needs enough stock to meet demand without tying up cash. We set inventory policy from measured forecast error and anchor replenishment to what shoppers actually buy at the shelf.
- **Safety stock from forecast error (Service-level targets):** We set safety stock and reorder points by item and location from measured forecast error and lead-time variability, against service-level targets tied to margin rather than rules of thumb. *Outcome:* Hold less inventory for the same service, or better service for the same stock.
- **POS-driven replenishment (Collaborative planning, forecasting and replenishment (CPFR)):** Replenishment anchored to store point-of-sale data aligns your orders with the retailer's sell-through, so both sides plan from one shared forecast, cutting promotional stockouts and improving inventory turns. *Outcome:* Share one forecast with your retail partner and replenish to real demand.
- **Promotion and seasonal builds (Pre-builds and promotion stock):** We plan inventory builds ahead of promotions, holidays and seasonal peaks from forecast lift and production lead times, then plan the sell-down so leftover stock doesn't linger after the event. *Outcome:* Have stock on shelf for the event without excess afterward.
- **Slow movers and spare parts (Croston's method):** Items that sell in irregular bursts with many zero weeks break standard methods. Croston's method forecasts demand size and interval separately, giving realistic stock levels for spare parts and the long tail. *Outcome:* Stop overstocking the tail while still covering the orders that come.
- **Distribution center allocation (Multi-echelon allocation):** We plan how much stock to hold at plants, distribution centers and stores together rather than one location at a time, positioning safety stock where it protects service at the lowest total cost. *Outcome:* Lower network inventory while keeping the right stock close to demand.
- **Inventory health (Turns, excess and obsolete, recoverable inventory):** We track turns, weeks of supply, excess and obsolete stock and stockouts by item and location, and size how much inventory can be released without hurting service. *Outcome:* Free up cash tied in excess stock and act before items go obsolete.

#### Supply Chain & Inventory Planning FAQs
- **What is supply chain & inventory planning?** Supply chain and inventory planning links the demand forecast to what you actually make, stock and ship, through safety stock, service levels, replenishment and capacity. RoadMap Technologies helps life science and consumer goods teams by connecting statistical forecasts to inventory policy and supply plans, so stock protects service and margin without tying up cash.
- **How do you set safety stock levels?** From measured forecast error and lead-time variability for each item and location, against a service-level target. That replaces rules of thumb like two weeks of cover, which overstock steady items and understock volatile ones.
- **How do you plan inventory for products with a short shelf life?** We plan against remaining shelf life and customer minimum dating, not just quantity. Lots at risk of expiry are flagged early enough to redeploy them, and safety stock is balanced against the cost of write-offs.
- **What is CPFR?** Collaborative planning, forecasting and replenishment is a process where a supplier and a retailer share one forecast, usually anchored to store point-of-sale data, and plan orders together. In our Samsung × Best Buy work it reduced promotional stockouts and improved inventory turns.
- **How do you forecast spare parts and slow-moving items?** With Croston's method, which forecasts the size of each order and the interval between orders separately. It suits items with many zero periods, where standard methods either overreact to each sale or forecast a little demand every week.

### Executive Decision Support

- **URL:** https://roadmap-tech.com/consulting-services/executive-decision-support/
- **Summary:** Long-range plans, portfolio scenarios and the KPIs leadership runs the business on. We align stakeholders on one number and build decision frameworks that hold up in leadership and board review.
- **Definition:** Executive decision support turns forecasts into decisions leadership can act on. RoadMap Technologies helps life science and consumer goods leadership teams by building long-range plans and portfolio scenarios, aligning stakeholders on the KPIs that matter, and setting a planning cadence and decision frameworks that hold up in leadership and board review.
- **Typical engagements:** Long-range plans for brands and portfolios; Loss-of-exclusivity and portfolio scenarios; Aligning finance and supply on one number; Standing up or resetting an S&OP or IBP process; Preparing leadership and board planning reviews

#### Life Sciences Applications
Long-range plans set budgets, investment and supply commitments years ahead. We build brand and portfolio LRPs on the same assumptions as the near-term forecast, with the uncertainty made explicit for leadership and the board.
- **Long-range plan (5–10 year brand and portfolio LRP):** We build brand and portfolio plans five to ten years out from patients, share, price and gross-to-net, linked to the operational forecast so the first two years match the S&OP number. *Outcome:* Give finance and leadership a long-range plan built on traceable assumptions.
- **Loss of exclusivity (Generic and biosimilar erosion curves):** Erosion curves calibrated to comparable molecules model how fast volume and price fall after generic or biosimilar entry, by channel and formulation, including authorized generics and the timing of each entrant. *Outcome:* Plan the revenue cliff, supply wind-down and lifecycle response before LOE arrives.
- **Portfolio valuation (rNPV and probability of technical and regulatory success):** We value pipeline and in-market assets on risk-adjusted NPV, applying the probability of technical and regulatory success at each phase, so assets with very different risk can be compared on one basis. *Outcome:* Rank investment and resource choices across the portfolio on a consistent basis.
- **Plan risk ranges (Monte Carlo P10, P50 and P90):** We put distributions on the assumptions that matter most, such as launch timing, peak share, LOE date and pricing, and simulate the plan thousands of times to show the realistic range. *Outcome:* Present the board a plan with its upside, downside and key risks named.
- **One number across functions (Integrated S&OP and IBP executive review):** We align brand, finance, supply and commercial operations on one demand number and one set of assumptions, and design the executive S&OP or integrated business planning review that signs it off. *Outcome:* End the debate over whose forecast is right and spend the meeting on decisions.
- **Business development support (In-licensing asset forecasts):** For in-licensing and acquisition opportunities, we build independent forecasts of the asset's patient opportunity, uptake and peak sales, with risk ranges, on a timeline that fits the deal process. *Outcome:* Go into negotiations with your own view of what the asset is worth.

#### Consumer Goods & Retail Applications
Leadership needs to see where volume, trade spend and capacity are heading over the next three to five years. We build the plan, the scenarios and the review cadence that keep those decisions grounded in data.
- **Category and volume plan (3–5 year long-range plan (LRP)):** We build the three-to-five year volume and revenue plan by category, brand and channel from growth, share, pricing and distribution assumptions, tied to the operational forecast so year one matches. *Outcome:* Set long-range targets and investment plans on assumptions everyone can see.
- **Trade-spend ROI and calendar planning (Next-year calendar builds and mid-course re-planning):** We evaluate the return on trade spend by key account, event type and brand, combining POS sell-through with shipments and deal costs to build next-year promotion calendars and run mid-course corrections when inflation, tariffs or weather shift category demand. *Outcome:* Reallocate trade budget toward the accounts and events that earn it back, and re-plan fast when conditions change.
- **KPI and planning cadence (S&OP and IBP leadership review):** We define the KPIs finance, sales, supply and operations will share, such as forecast accuracy, bias, service level and inventory, and set the monthly calendar and templates for the leadership review. *Outcome:* Run a planning cycle teams actually follow, with one set of measures.
- **SKU rationalization (Tail analysis and portfolio mix):** We rank SKUs by volume, margin, forecastability and the incremental sales lost if each were cut, so the tail can be trimmed without losing shoppers to competitors. *Outcome:* Cut complexity and cost while keeping the volume that matters.
- **Leadership scenarios (Risk ranges tied to dollars):** We translate demand scenarios into revenue, margin, inventory and cash, with probability ranges on the key assumptions, so leadership weighs options in financial terms rather than units. *Outcome:* Make pricing, investment and capacity calls with the financial downside in view.
- **Capacity and network decisions (Investment cases):** We build the demand case behind capacity, co-manufacturing and distribution network investments, testing each option against long-range volume scenarios so the decision holds up if demand shifts. *Outcome:* Commit capital to capacity with the demand risk measured upfront.

#### Executive Decision Support FAQs
- **What is executive decision support?** Executive decision support turns forecasts into decisions leadership can act on. RoadMap Technologies helps life science and consumer goods leadership teams by building long-range plans and portfolio scenarios, aligning stakeholders on the KPIs that matter, and setting a planning cadence and decision frameworks that hold up in leadership and board review.
- **What goes into a pharma long-range plan?** A brand or portfolio long-range plan usually covers five to ten years, including patient numbers, share, pricing and gross-to-net, launch timing for pipeline assets, and loss-of-exclusivity erosion. We link the first two years to the operational forecast and attach risk ranges to the assumptions that matter most.
- **How do you forecast loss of exclusivity?** We calibrate erosion curves to comparable molecules, separating small molecules facing generics from biologics facing biosimilars, and model volume and price by channel and formulation. Entry timing, the number of entrants and authorized generics are treated as scenarios with their own probabilities.
- **How do you get finance, sales and supply to agree on one number?** By building their plans from one model and one set of written assumptions, then agreeing who owns each assumption and when it can change. The executive review then debates the assumptions and the gap to target, not whose spreadsheet is right.
- **How often should the long-range plan be refreshed?** Most teams rebuild it annually with the budget and refresh it quarterly, or sooner when a major event hits, such as a trial readout, a label change or a competitor launch. Because it shares a model with the operational forecast, each refresh starts from current numbers instead of a fresh spreadsheet.

### Advanced Analytics

- **URL:** https://roadmap-tech.com/consulting-services/advanced-analytics/
- **Summary:** When the question doesn't fit a standard model: simulation, optimization, machine learning and large-batch forecasting, built in R and Python. The same methods run inside every service we offer.
- **Definition:** Advanced analytics is purpose-built modeling for questions a standard forecasting tool can't answer. RoadMap Technologies helps life science and consumer goods teams by building Monte Carlo simulations, optimization models, machine learning and large-batch forecasting in R and Python, using the Geneva engine where it fits and custom models where it doesn't.
- **Typical engagements:** Monte Carlo simulation of supply, program or portfolio risk; Trade promotion calendar optimization and what-if scenario modeling; Large-batch forecasting through the Geneva API; Independent review of in-house or vendor forecast models

#### Life Sciences Applications
For supply, commercial and portfolio questions that don't fit a standard model. We build simulation, optimization and machine learning, and independently test the models you already rely on.
- **Simulation (Monte Carlo on supply, program or portfolio risk):** We simulate thousands of possible futures for supply, program spend or portfolio value, with distributions on the inputs that matter, such as yield, demand, timing and probability of success. *Outcome:* Make decisions against the range of outcomes, with the biggest risks quantified.
- **Optimization (Allocation and network optimization):** Mathematical optimization finds the best allocation of constrained supply, field resources or budget across products, accounts and regions, subject to the business rules and capacity limits you set. *Outcome:* Replace spreadsheet trade-offs with the allocation that does the most within your limits.
- **Large-batch forecasting (Thousands of NDC × account series):** We forecast every NDC, account and channel combination in one automated run on the Geneva engine, with best-fit method selection and accuracy reported per series, refreshed on your planning cadence. *Outcome:* Cover the full portfolio at account level without adding planners.
- **Patient-level machine learning (Discontinuation risk with SHAP explanations):** Gradient-boosted models on de-identified patient-level data score the risk of discontinuation or switching, and SHAP values explain which factors drive each prediction, so results can be acted on and defended. *Outcome:* Target patient support where it prevents the most discontinuations.
- **Model review and validation (Independent audit of in-house or vendor forecasts):** We review the assumptions, data, methods and accuracy of forecasts built in-house or by vendors, back-test them against actuals, and document what holds up and what should change. *Outcome:* Go into budget and board reviews with a forecast that has been independently tested.
- **Custom R and Python builds (Documented and handed off):** When nothing off the shelf fits, we build the model in R or Python, document the code and assumptions, and hand it to your team with training, so it doesn't depend on us. *Outcome:* Own a model your analysts can run, explain and extend.

#### Consumer Goods & Retail Applications
For trade, pricing and supply questions that outgrow standard tools. We optimize promotion calendars, simulate scenarios and forecast at scale, and stress-test the models your teams already use.
- **Promotion calendar optimization (What-if calendars on POS and shipment data):** We combine NielsenIQ and Circana point-of-sale data with internal shipments, deal costs and trade performance, then run what-if scenarios to select which events to run, when, and at what depth across the year. We also support mid-course corrections when weather, tariffs or inflation change the picture. *Outcome:* Evaluate alternative calendars in minutes and get more incremental profit from your trade budget.
- **Batch forecasting (Geneva API at scale):** The Geneva API forecasts thousands of SKU, store and channel series in one request, with automatic method selection, so large catalogs get a statistical baseline every cycle without manual work. *Outcome:* Refresh every item-location forecast on schedule, at a fraction of the manual effort.
- **ML demand models (Gradient boosting with SHAP explanations):** Gradient-boosted models combine price, promotion, weather, events and store attributes in one demand model, and SHAP values show how much each factor contributed, so planners can see why the number moved. *Outcome:* Capture complex driver interactions without losing the explanation.
- **Hierarchical forecasting (Reconciled SKU, store and region totals):** We forecast at every level of the product and location hierarchy and reconcile them, so SKU and store forecasts add up to the region and brand totals that finance and sales plan to. *Outcome:* Give every team numbers that add up, from store shelf to annual plan.
- **Model review and validation (Independent audit against a benchmark):** We test in-house or vendor demand and promotion models against actuals, check the data and assumptions, and compare them with a statistical benchmark, so you know whether the model is earning its keep. *Outcome:* Decide whether to keep, fix or replace a model on evidence.
- **Scenario simulation (Monte Carlo on the plan):** We run the annual plan thousands of times across plausible price, lift, competitor and supply outcomes, so you see the range of results instead of a single number. *Outcome:* Go into annual planning and retailer negotiations knowing the downside as well as the target.

#### Advanced Analytics FAQs
- **What is advanced analytics?** Advanced analytics is purpose-built modeling for questions a standard forecasting tool can't answer. RoadMap Technologies helps life science and consumer goods teams by building Monte Carlo simulations, optimization models, machine learning and large-batch forecasting in R and Python, using the Geneva engine where it fits and custom models where it doesn't.
- **When does a problem need advanced analytics instead of a standard forecast?** When the question involves constraints, uncertainty or scale that a standard forecasting tool wasn't built for, such as allocating short supply, valuing a portfolio under risk, or forecasting hundreds of thousands of series. If a standard model is enough, we'll say so.
- **Can you review a forecast model built by our team or a vendor?** Yes. We review the data, assumptions and methods, back-test the model against actuals, and compare it with a statistical benchmark. You get a written assessment of what holds up and what should change.
- **Which tools do your analysts build with?** Mostly R and Python, with the Geneva Forecasting™ Engine for statistical forecasting at scale. We build on your infrastructure or ours, and document the code so your team can run and maintain it.
- **How do you make machine learning models explainable?** We use SHAP values, which show how much each input, such as price, promotion or a patient attribute, pushed each prediction up or down. Planners and reviewers can see why the model gave the answer it did.

---

## Data Services

Hub URL: https://roadmap-tech.com/data-services/

Secure pipelines, warehouses and governance that give your forecasts complete, current data.

### Data Pipeline Engineering

- **URL:** https://roadmap-tech.com/data-services/data-pipeline-engineering/
- **Summary:** Automated ETL and ELT pipelines, managed SFTP servers with 2FA, and quality gates that keep planning data complete and current.
- **Definition:** Data pipeline engineering builds the automated flows that move data from source systems and external partners into data warehouses and forecasting tools. RoadMap Technologies designs cloud and on-premises ETL/ELT pipelines, sets up hardened SFTP servers with two-factor authentication (2FA), and enforces automated quality gates, SLAs, monitoring, and runbooks so forecasts always run on complete, current data.
- **Typical engagements:** Managed SFTP servers with two-factor authentication (2FA) for partner drops; Aggregating multi-partner healthcare data across EDI 852/867, specialty pharmacy, and claims; Feeding daily point-of-sale and ERP shipment data into demand planning; Hardening legacy scripts with automated quality gates, retries, and alerting

#### Life Sciences Applications
Commercial and clinical data arrives from dozens of specialty pharmacies, wholesalers, hubs, and claims aggregators on different schedules and formats. We build secure, automated pipelines that ingest, validate, and normalize every feed before it reaches your warehouse or forecast.
- **Managed SFTP with 2FA (Hardened partner drop zones with MFA and encryption):** We provision and manage dedicated SFTP servers protected by two-factor authentication (SSH key plus TOTP/MFA), IP allowlisting, chroot directory isolation, and automated PGP decryption as soon as partner files land. *Outcome:* Give specialty pharmacies, wholesalers, and data vendors a secure, audit-ready drop zone.
- **Multi-partner aggregation (Specialty pharmacy, hub, and distributor feeds):** Each specialty pharmacy and patient hub uses its own layout, patient status codes, and delivery cadence. Our pipelines standardize every partner feed into one canonical schema with patient and account cross-walking. *Outcome:* View starts, refills, and dispenses across your entire distribution network in one table.
- **852 and 867 channel pipelines (Wholesaler inventory and sales-out automation):** Automated ingestion of EDI 852 product activity and 867 sales-out files reconciles wholesaler receipts, inventory on hand, and downstream pharmacy or hospital shipments daily and weekly. *Outcome:* Keep sell-in versus demand models and weeks-on-hand dashboards current without manual file prep.
- **Pre-load quality gates (Quarantine and schema validation):** Every incoming file is checked for row counts, date completeness, NDC formatting, duplicate records, and sudden volume spikes before loading. Malformed files are quarantined with instant alerts to the data team. *Outcome:* Catch late or corrupted vendor files at the gate before they distort a brand forecast.
- **De-identified clinical and claims flows (Tokenized APLD and JSON trial pipelines):** Pipelines integrate HIPAA-aligned de-identification and longitudinal token matching inline, stripping protected health information and normalizing JSON or flat-file claims before landing in analytics tables. *Outcome:* Analyze longitudinal patient journeys safely without exposing sensitive identifiers.
- **SLA monitoring and runbooks (Automated retries, dead-letter queues, and hand-off):** We instrument every pipeline job with execution logs, SLA timers, automated retries for transient network drops, and clear operational runbooks so your internal IT team or ours can run it with confidence. *Outcome:* Know immediately when a partner feed is late and how to resolve it in minutes.

#### Consumer Goods & Retail Applications
High-velocity retail and CPG planning depends on daily point-of-sale feeds, ERP shipments, open orders, and warehouse inventory arriving on time and aligning to the same product and customer hierarchy.
- **Syndicated and retailer POS ingestion (NielsenIQ, Circana, and direct retail feeds):** We automate the retrieval, validation, and loading of syndicated scanner data alongside direct retailer POS and inventory feeds into your planning warehouse. *Outcome:* Start every weekly planning cycle with reconciled sell-through data already loaded.
- **ERP to forecasting pipelines (Automated feeds for RoadMap GPS, TrailBlazer, and Geneva API):** Scheduled pipelines extract historical shipments, open orders, on-hand inventory, and item master updates from SAP, Oracle, NetSuite, or Dynamics and load them directly into RoadMap forecasting tools. *Outcome:* Eliminate manual CSV exports and spreadsheet copy-paste before running forecasts.
- **Secure B2B file exchange (SFTP servers with 2FA for retail and 3PL partners):** For retail partners, co-manufacturers, and 3PL warehouses that exchange flat files or EDI batches, we stand up 2FA-protected SFTP endpoints with event-driven ingestion triggers and archive retention. *Outcome:* Replace unsecured email attachments and brittle FTP scripts with governed transfers.
- **Hierarchy and calendar normalization (Retail 4-4-5, weekly, and monthly alignment):** Pipelines automatically translate UPCs to internal SKU codes, map ship-to locations to retail banners, and align retail 4-4-5 calendars with fiscal months so POS and shipment histories match period for period. *Outcome:* Compare sell-in shipments and sell-through POS on the exact same calendar and hierarchy.
- **In-flight data quality controls (Anomaly detection and unit-of-measure checks):** Automated rules verify cases-to-eaches conversions, currency rates, price bounds, and missing store reports during the ETL run, flagging exceptions before downstream batch forecasts execute. *Outcome:* Prevent a single bad unit conversion or missing banner file from skewing thousands of SKU forecasts.
- **Cloud and on-premises orchestration (SQL Server, Snowflake, Oracle, and hybrid scheduling):** Whether your data lives in on-premises Microsoft SQL Server or Oracle databases, or in Snowflake, Azure, or AWS, we build pipelines native to your stack with full version control and documentation. *Outcome:* Run reliable data pipelines on the infrastructure your security and IT policies require.

#### Data Pipeline Engineering FAQs
- **What is data pipeline engineering?** Data pipeline engineering builds the automated flows that move data from source systems and external partners into data warehouses and forecasting tools. RoadMap Technologies designs cloud and on-premises ETL/ELT pipelines, sets up hardened SFTP servers with two-factor authentication (2FA), and enforces automated quality gates, SLAs, monitoring, and runbooks so forecasts always run on complete, current data.
- **Can RoadMap set up and manage secure SFTP servers with two-factor authentication (2FA)?** Yes. We provision and operate hardened SFTP servers with two-factor authentication (SSH key plus TOTP/MFA), IP allowlisting, chroot directory isolation for each external partner, and automatic PGP/GPG decryption that triggers ingestion as soon as files arrive.
- **What happens when an external data partner sends a late or malformed file?** Every pipeline includes automated pre-load quality gates checking row counts, schema drift, date completeness, and duplicate keys. If a file fails validation or misses its SLA window, it is quarantined before touching production tables and an immediate alert is sent with diagnostic details.
- **Which healthcare and retail data feeds do your pipelines handle?** In life sciences, we ingest specialty pharmacy dispenses, patient hub status files, EDI 852/867 wholesaler movements, and anonymized patient-level claims (APLD). In consumer goods and retail, we ingest NielsenIQ and Circana POS feeds, retailer EDI, 3PL inventory, and ERP shipment actuals.
- **Who operates the data pipelines after they are built?** We can operate and monitor the pipelines for you under an agreed SLA, or deploy them inside your environment with complete documentation, source control, alerting, and runbooks for your internal data engineering team.

### Data Warehousing & Modeling

- **URL:** https://roadmap-tech.com/data-services/data-warehousing-modeling/
- **Summary:** Cloud and on-premises data warehouses and dimensional models engineered for fast forecasting, S&OP, and executive reporting.
- **Definition:** Data warehousing and modeling structures enterprise data so it answers business and planning questions at scale. RoadMap Technologies designs, tunes, and migrates both on-premises databases (Microsoft SQL Server, Oracle Database) and cloud data warehouses (Snowflake, Oracle Cloud, Azure, AWS), building dimensional schemas and planning marts tailored for forecasting, S&OP, and OLAP reporting.
- **Typical engagements:** Designing cloud, on-premises, and hybrid enterprise data warehouses; Building dedicated S&OP, demand planning, and gross-to-net data marts; Modeling multi-level product, customer, channel, and payer hierarchies; Tuning slow queries, indexing, and partitioning for millions of time series

#### Life Sciences Applications
Life science commercial and supply data spans patient cohorts, specialty pharmacies, wholesalers, payers, and gross-to-net contracts. We design cloud and on-premises warehouses that unify these sources into governed schemas built for patient-based forecasting and long-range planning.
- **Commercial & S&OP data marts (Unified patient, channel, and shipment schemas):** We design dimensional star and snowflake schemas that link ex-factory shipments, 852/867 wholesaler movements, specialty pharmacy dispenses, and patient starts around shared product, time, and account dimensions. *Outcome:* Give brand, finance, and supply teams one governed warehouse to forecast and report from.
- **Cloud and on-premises deployments (SQL Server, Oracle, Snowflake, and OCI):** Whether your security posture requires an on-premises Microsoft SQL Server or Oracle Database behind your firewall, or a cloud warehouse in Snowflake, AWS, Azure, or Oracle Cloud, we architect and tune the environment end to end. *Outcome:* Deploy your planning warehouse in the exact cloud or on-premises environment your IT team mandates.
- **Longitudinal patient data modeling (Cohort, persistency, and dosing tables):** Raw claims and hub records are structured into longitudinal patient-month cohorts with pre-calculated persistency, compliance (PDC, MPR, DACON), and line-of-therapy attributes ready for econometric and survival modeling. *Outcome:* Cut patient-funnel model refresh times from days of ad-hoc SQL to minutes.
- **Gross-to-net data structures (Channel, payer, chargeback, and rebate marts):** We model gross sales, wholesaler chargebacks, Medicaid and 340B utilization, commercial rebates, and co-pay assistance by NDC and channel so gross-to-net reconciliations trace cleanly to unit forecasts. *Outcome:* Connect unit demand forecasts directly to net revenue and accrual reporting.
- **Snapshot and version history (Slowly changing dimensions and forecast archives):** Every S&OP cycle, assumption update, and hierarchy restatement is stored as an immutable versioned snapshot, allowing analysts to compare any historical plan against actuals even after territory or brand realignments. *Outcome:* Measure forecast accuracy and bias across cycles without losing historical context.
- **Query & batch performance tuning (Partitioning, indexing, and compute optimization):** We optimize table partitioning, columnstore indexes, materialized views, and warehouse compute sizing so multi-year cohort queries and RoadMap GPS 360 rollups return in seconds while keeping cloud spend predictable. *Outcome:* Eliminate slow dashboard loads and overnight batch bottlenecks.

#### Consumer Goods & Retail Applications
Consumer goods and retail planning requires fast rollups from individual store and SKU combinations up to brand, category, key account, and total company views across years of weekly and daily history.
- **Multi-tier hierarchy modeling (SKU-to-brand and ship-to-to-banner rollups):** We model alternate and ragged hierarchies across products (UPC, SKU, pack, brand, category) and customers (store, DC, ship-to, retail banner, channel) so forecasts reconcile automatically at every level. *Outcome:* Let sales plan by account, marketing by brand, and supply by DC from the exact same database.
- **RoadMap GPS & SQL Server backends (High-performance relational & OLAP schemas):** RoadMap GPS and GPS 360 run on Microsoft SQL Server to handle massive enterprise planning datasets. We design, index, and maintain the underlying SQL Server schemas, stored procedures, and OLAP views for sub-second slice-and-dice. *Outcome:* Scale spreadsheet-familiar planning to hundreds of thousands of series without file bloat.
- **POS and CPFR data warehousing (Store-level sell-through and inventory marts):** Store-week point-of-sale data from NielsenIQ, Circana, and retail partners is warehoused alongside internal shipments, DC inventory, and open orders to power collaborative replenishment and demand sensing. *Outcome:* Query years of SKU-by-store velocity and on-hand balance without hitting row limits.
- **Trade promotion and pricing repositories (Event calendars, lift baselines, and deal costs):** We structure historical promotion calendars, feature/display flags, everyday and promoted price points, and trade funding into clean analytical tables ready for elasticity and lift decomposition models. *Outcome:* Give revenue management a single historical ledger of every promotion and what it earned.
- **Legacy-to-cloud warehouse migration (On-premises SQL/Oracle to Snowflake or Azure):** When transitioning from legacy on-premises databases or scattered Access/Excel marts to Snowflake, Azure Synapse, or AWS Redshift, we migrate schemas, rewrite stored procedures, and validate parallel outputs. *Outcome:* Modernize your data stack without disrupting active S&OP cycles or downstream reports.
- **Cost and workload governance (Storage tiering and warehouse sizing):** For cloud warehouses, we separate ingestion, batch forecasting, and BI reporting workloads, configure auto-suspend and clustering keys, and eliminate redundant table scans that inflate monthly cloud bills. *Outcome:* Keep query latency low and cloud warehouse bills under control as data volume grows.

#### Data Warehousing & Modeling FAQs
- **What is data warehousing & modeling?** Data warehousing and modeling structures enterprise data so it answers business and planning questions at scale. RoadMap Technologies designs, tunes, and migrates both on-premises databases (Microsoft SQL Server, Oracle Database) and cloud data warehouses (Snowflake, Oracle Cloud, Azure, AWS), building dimensional schemas and planning marts tailored for forecasting, S&OP, and OLAP reporting.
- **Do you support both on-premises SQL Server/Oracle and cloud warehouses like Snowflake?** Yes. We architect, tune, and maintain on-premises Microsoft SQL Server and Oracle databases, cloud warehouses including Snowflake, Oracle Cloud Infrastructure, Azure, and AWS Redshift, and hybrid deployments that sync a cloud warehouse with a dedicated SQL Server planning mart.
- **How is a forecasting data mart different from a standard corporate warehouse?** A forecasting data mart enforces continuous time spines (preserving zero-demand periods for intermittent demand models), links predecessor and successor SKUs across packaging transitions, reconciles ragged product and customer hierarchies, and stores immutable snapshots of every historical forecast cycle.
- **Can you migrate our legacy on-premises planning database to the cloud without breaking S&OP?** Yes. We migrate schemas, tables, and stored procedures in phases, run parallel validation to verify that every rollup and report matches to the penny, and cut over between planning cycles so active S&OP meetings are never disrupted.
- **How do you improve slow query and batch performance on large datasets?** We optimize table partitioning, columnstore and covering indexes, materialized OLAP views, and warehouse compute sizing, routinely reducing multi-hour batch loads and slow dashboard queries to seconds.

### Systems Integration

- **URL:** https://roadmap-tech.com/data-services/systems-integration/
- **Summary:** Bi-directional integration and automated pipelines connecting ERP, CRM, POS, and RoadMap forecasting software into one source of truth.
- **Definition:** Systems integration connects ERP, CRM, point-of-sale, and demand planning software so commercial, finance, and supply chain teams operate from one source of truth. RoadMap Technologies integrates platforms such as SAP, Oracle, NetSuite, Microsoft Dynamics, Salesforce, and Veeva directly with RoadMap GPS, RoadMap GPS 360, TrailBlazer, and the Geneva Forecasting™ API across cloud and on-premises environments.
- **Typical engagements:** Bi-directional integration between ERP, CRM, and demand forecasting systems; Writing approved consensus forecasts and DRP/MRP reorder plans back into your ERP; Combining CRM pipeline and commercial activity with historical shipment baselines; Consolidating multi-ERP and master data hierarchies after an acquisition

#### Life Sciences Applications
In life sciences, commercial activity lives in Veeva or Salesforce, financial actuals and inventory live in SAP or Oracle ERP, and channel movements arrive via 3PL and specialty pharmacy feeds. We connect these systems and wire them directly into your forecasting platform.
- **ERP to RoadMap GPS & GPS 360 integration (SAP, Oracle, and NetSuite connectors):** We build automated, bi-directional integrations between your ERP (SAP S/4HANA or ECC, Oracle E-Business Suite or Cloud ERP, NetSuite) and RoadMap GPS or GPS 360, pulling ex-factory shipments, lot inventory, and open orders on schedule. *Outcome:* Keep your planning workspace synced with ERP actuals without manual file exports.
- **CRM & commercial activity integration (Veeva and Salesforce alignment):** Field call activity, target account lists, formulary status updates, and medical-account milestones from Veeva CRM or Salesforce are piped into your planning database and mapped to territory and brand hierarchies. *Outcome:* Measure promotional response and align commercial forecasts with live field execution.
- **Supply plan & MRP write-back (Approved demand to production planning):** Once leadership signs off on the monthly consensus forecast or 3-to-10 year supply plan, our integration formats and pushes time-phased net demand by NDC and packaging site back into your ERP or supply planning module. *Outcome:* Close the loop between commercial forecasting and manufacturing execution automatically.
- **3PL & serialization hub connectivity (Automated inventory and shipment sync):** For emerging biotechs and specialty pharma teams relying on third-party logistics providers, we integrate 3PL ERP extracts directly with your internal finance and forecasting models. *Outcome:* Gain enterprise-grade visibility across outsourced distribution networks.
- **Gross-to-net & FP&A integration (Connecting unit plans to financial ledgers):** We connect unit and patient forecasts in RoadMap GPS 360 with contract management and corporate FP&A systems so gross sales, rebate accruals, and net revenue projections update in lockstep. *Outcome:* Eliminate reconciliation gaps between commercial operations and corporate finance.
- **Post-acquisition system unification (Multi-ERP master data harmonization):** After an acquisition or in-licensing deal, we build an integration layer that maps disparate product codes, customer accounts, and chart-of-accounts structures into one unified planning hierarchy before a full ERP migration completes. *Outcome:* Forecast and report across newly acquired brands immediately after close.

#### Consumer Goods & Retail Applications
Consumer goods, electronics, and manufacturing teams lose hours every week copying numbers between ERP, CRM, POS portals, and spreadsheets. We connect your operational systems directly to RoadMap forecasting software and automate the data pipelines between them.
- **Closed-loop ERP forecasting (Pull history, run Geneva, push replenishment):** We build end-to-end pipelines that extract SKU-by-location shipment history and on-hand stock from SAP, NetSuite, Oracle, or Dynamics, run best-fit forecasts in RoadMap GPS or the Geneva API, and write safety stock and reorder quantities back to the ERP. *Outcome:* Turn statistical forecasts into purchase orders and work orders without manual re-keying.
- **CRM pipeline & quota integration (Salesforce opportunities to demand plans):** Key-account promotional commitments, new distribution authorizations, and B2B sales pipeline from Salesforce or HubSpot are integrated alongside statistical baselines so S&OP reviews see committed deals next to historical trends. *Outcome:* Ground sales-forecast overrides and territory quotas in live CRM data.
- **TrailBlazer & Geneva API embedding (REST API, Python SDK, and webhook integration):** For engineering and operations teams with custom internal portals or ERPs, we embed the Geneva Forecasting™ API (averaging under 200 ms per series) directly into your application workflows and database triggers. *Outcome:* Add Oracle-proven statistical forecasting inside the software your planners already use.
- **Master data synchronization (Automated SKU, BOM, and customer alignment):** When new SKUs, bills of materials (BOMs), price lists, or customer ship-to locations are created in the ERP, our integration pipelines propagate those master data updates and like-item mappings into your forecasting environment automatically. *Outcome:* Ensure new launches and active SKUs never drop out of the forecast due to missing master data.
- **Ecommerce & omnichannel integration (Direct-to-consumer and retail wholesale sync):** We unify Shopify or direct-to-consumer order streams with wholesale ERP shipments and 3PL warehouse balances so omnichannel brands forecast total inventory needs across DTC and retail channels together. *Outcome:* Prevent wholesale promotions from starving direct-to-consumer inventory, and vice versa.
- **Hybrid cloud-to-on-premises bridges (Secure connectors across network boundaries):** When your ERP runs on-premises (such as SQL Server or legacy SAP/Oracle) and your CRM or analytics run in the cloud, we deploy encrypted, 2FA-authenticated bridge pipelines that sync both sides safely. *Outcome:* Connect cloud and on-premises systems without exposing internal databases to the public internet.

#### Systems Integration FAQs
- **What is systems integration?** Systems integration connects ERP, CRM, point-of-sale, and demand planning software so commercial, finance, and supply chain teams operate from one source of truth. RoadMap Technologies integrates platforms such as SAP, Oracle, NetSuite, Microsoft Dynamics, Salesforce, and Veeva directly with RoadMap GPS, RoadMap GPS 360, TrailBlazer, and the Geneva Forecasting™ API across cloud and on-premises environments.
- **Can you integrate RoadMap GPS, TrailBlazer, and the Geneva API directly with our ERP?** Yes. We build automated connectors and pipelines for SAP (S/4HANA and ECC), Oracle (Cloud ERP, E-Business Suite, NetSuite), Microsoft Dynamics 365, and other ERPs to pull historical actuals, open orders, and inventory and write approved forecasts and reorder plans back.
- **How does CRM data from Salesforce or Veeva fit into the demand forecast?** We integrate key-account promotional commitments, new distribution wins, contract pricing, and field call activity from Salesforce or Veeva into the planning warehouse so planners and econometric models can combine commercial pipeline with shipment baselines.
- **Can you connect on-premises ERP databases with cloud analytics or CRM platforms?** Yes. We engineer encrypted hybrid bridge pipelines with 2FA authentication and IP allowlisting that synchronize on-premises SQL Server, Oracle, or SAP databases with cloud warehouses and SaaS tools without exposing internal ports.
- **How do you integrate data across multiple ERPs after an acquisition?** We build a canonical integration and master-data cross-walk layer that harmonizes product codes, customer hierarchies, units of measure, and currencies across the acquired and parent ERPs so leadership gets one consolidated forecast immediately.

### Data Governance & Quality

- **URL:** https://roadmap-tech.com/data-services/data-governance-quality/
- **Summary:** Automated pipeline quality gates, source-to-target lineage, and KPI controls so every team plans from one trusted number.
- **Definition:** Data governance and quality establishes the automated validation rules, source-to-target lineage, and master data controls that make planning numbers trustworthy. RoadMap Technologies embeds quality checks directly inside your data pipelines, reconciles product and customer hierarchies, and standardizes KPI definitions so finance, commercial, and supply teams work from one governed source of truth.
- **Typical engagements:** Embedding automated quality gates and quarantine checks inside every data pipeline; Aligning finance, sales, and supply on one governed definition of net sales and demand; Catching late, duplicate, or incomplete partner files before they reach the forecast; Documenting audit-ready source-to-target lineage for regulated planning data

#### Life Sciences Applications
In life sciences, a single unmapped specialty pharmacy code, duplicate 867 shipment record, or misapplied chargeback rule can throw off brand forecasts and gross-to-net accruals. We build automated validation and lineage controls across every feed.
- **In-pipeline quality gates (Automated freshness, completeness, and schema checks):** Every specialty pharmacy, hub, and wholesaler feed passes through automated pre-load rules checking row counts, expected date ranges, NDC check digits, and partner file completeness before touching warehouse tables. *Outcome:* Block corrupted or partial partner submissions automatically before forecasts run.
- **Quarantine and exception routing (Hold bad records without halting the pipeline):** Records with unmapped account IDs, negative quantities, or out-of-bounds pricing are routed to a dedicated quarantine table with automated alerts, allowing clean records to load on schedule while exceptions are resolved. *Outcome:* Keep S&OP timelines on track while maintaining 100% visibility into data anomalies.
- **Gross-to-net & revenue reconciliation (One number across commercial and finance):** We codify the exact business rules connecting ex-factory shipments, wholesaler inventory changes, chargebacks, 340B, Medicaid, and commercial rebates so finance and brand planning query the exact same net definitions. *Outcome:* End executive review debates over why commercial and finance numbers differ.
- **Source-to-target data lineage (Field-level traceability from raw file to KPI):** Every transformation from the raw SFTP drop file through de-identification, cohort aggregation, and the RoadMap GPS 360 forecast table is documented and tagged with batch IDs and timestamps. *Outcome:* Answer internal audit, compliance, and board questions with complete lineage back to the source file.
- **Master data and cross-walk governance (Prescriber, account, and payer master alignment):** We maintain governed cross-walk tables linking DEA, NPI, HIN, and partner-specific account identifiers to a single canonical customer and territory hierarchy, with versioned effective dates when territories realign. *Outcome:* Prevent territory realignments or account ID changes from breaking historical trend lines.
- **Historical data cleansing for modeling (Outlier tagging, stockout imputation, and restatements):** Before standing up a new demand model, we audit historical series for one-time channel buy-ins, supply allocation periods, and reporting gaps so statistical baselines learn from true demand rather than data artifacts. *Outcome:* Improve baseline forecast accuracy immediately by feeding the engine clean history.

#### Consumer Goods & Retail Applications
When sales looks at gross shipments, marketing looks at syndicated POS, and supply chain looks at net orders in cases, S&OP meetings stall over whose spreadsheet is right. We govern the pipelines, hierarchies, and KPI rules so every team works from one number.
- **Automated POS & ERP validation (Pre-forecast pipeline quality controls):** Pipelines automatically check incoming ERP shipments and NielsenIQ/Circana POS files for missing retail banners, duplicate invoice lines, unit-of-measure mismatches, and sudden volume spikes before triggering batch forecasts. *Outcome:* Trust that weekly baselines in RoadMap GPS and TrailBlazer ran on verified inputs.
- **Unified KPI & business glossary (Governed definitions for cases, dollars, and net demand):** We establish and enforce one calculation for gross sales, net sales, trade spend, incremental promotional lift, and service level inside the warehouse so every dashboard and export reflects the same logic. *Outcome:* Eliminate conflicting spreadsheet formulas across sales, marketing, finance, and supply.
- **Product lifecycle & SKU chaining (Predecessor-to-successor mapping rules):** When packaging updates, gram weights change, or a new UPC replaces an existing item, governed supersession tables stitch the historical demand series together cleanly without double-counting overlap weeks. *Outcome:* Preserve years of seasonal history when items transition to new SKU numbers.
- **Hierarchy & master data stewardship (Automated unmapped-item and customer alerts):** Whenever a new SKU or ship-to customer appears in the ERP without a corresponding planning hierarchy assignment, the governance layer flags the steward immediately and assigns a default rule so nothing drops from totals. *Outcome:* Guarantee that SKU and account rollups always equal 100% of corporate totals.
- **History scrubbing & stockout adjustment (Distinguishing demand drops from supply shortages):** Historical weeks where shipments fell due to warehouse stockouts or port delays are flagged and adjusted so statistical models do not repeat past supply failures as next year's seasonal trough. *Outcome:* Stop past stockouts from biasing future forecasts downward.
- **Change control & override audit trails (Timestamped accountability for every adjustment):** Every master-data edit, business-rule update, and manual forecast override is logged with user ID, timestamp, reason code, and before/after values, supporting full Forecast Value Added (FVA) governance. *Outcome:* Know who changed the plan, when, and whether the change improved accuracy.

#### Data Governance & Quality FAQs
- **What is data governance & quality?** Data governance and quality establishes the automated validation rules, source-to-target lineage, and master data controls that make planning numbers trustworthy. RoadMap Technologies embeds quality checks directly inside your data pipelines, reconciles product and customer hierarchies, and standardizes KPI definitions so finance, commercial, and supply teams work from one governed source of truth.
- **How do automated quality gates protect our demand forecasts?** Quality gates inspect incoming ERP, CRM, and partner files in staging before batch forecasts run. By catching missing retail banners, unit-of-measure mismatches, unmapped NDC/SKU codes, and one-time data spikes upfront, they prevent bad inputs from distorting statistical baselines.
- **How do you handle unmapped SKUs or new customer accounts that appear in the ERP?** Our governance pipelines cross-check every incoming transaction against master dimension tables. New or unmapped items and ship-to accounts trigger an automated steward alert and apply a governed default rule so rollups always equal 100% of company totals.
- **What is source-to-target lineage and why does it matter for audits?** Source-to-target lineage tracks every metric on an executive dashboard or regulatory report back through each SQL or Python transformation to the exact raw SFTP file or ERP table, complete with batch IDs and timestamps.
- **Can you clean and restate historical data before we launch a new forecasting tool?** Yes. We audit historical series to chain superseded SKUs, impute or flag historical stockout periods, remove duplicate transactions, and align fiscal and 4-4-5 calendars so your forecasting engine starts with clean history.

### Automated Reporting & Dashboards

- **URL:** https://roadmap-tech.com/data-services/automated-reporting-dashboards/
- **Summary:** Automated daily and weekly S&OP packs, plan-vs-actual dashboards, and OLAP drill-downs delivered without manual spreadsheet work.
- **Definition:** Automated reporting and dashboards deliver the operational, commercial, and financial metrics leadership watches on a scheduled, hands-off cadence. RoadMap Technologies builds OLAP-style views, plan-versus-actual scorecards, forecast accuracy and Forecast Value Added (FVA) reports, and exception alerts that refresh daily or weekly directly from your warehouse and forecasting engine.
- **Typical engagements:** Generating weekly and monthly S&OP executive packs automatically; Tracking daily sales, orders, and shipments against the approved forecast; Scoring forecast accuracy and Forecast Value Added (FVA) by planner and SKU; Drilling down from total-company revenue to brand, region, account, and item

#### Life Sciences Applications
Brand, commercial operations, supply chain, and finance leadership need a current read on patient starts, channel inventory, and performance against the forecast and long-range plan without waiting days for analysts to assemble slides.
- **Executive brand & portfolio scorecards (Plan vs. actual across patients, units, and net revenue):** Automated dashboards track actual patient starts, total prescriptions, ex-factory shipments, and net revenue against the operating plan and most recent forecast across every brand and indication. *Outcome:* Give leadership one live view of commercial and financial performance every Monday morning.
- **Channel inventory & 852/867 monitoring (Wholesaler weeks on hand and IMA compliance):** Daily and weekly reports calculate days and weeks of inventory on hand by wholesaler and specialty distributor against contracted Inventory Management Agreement (IMA) bands, flagging build-ups or low stock early. *Outcome:* Spot channel loading or potential distributor stockouts before quarter-end.
- **Launch tracker dashboards (Weekly uptake, access, and persistency vs. launch curve):** For new brands and indications, automated trackers compare weekly NBRx, refill persistency, payer coverage wins, and territory adoption against the pre-launch P10/P50/P90 forecast curves. *Outcome:* See within weeks whether a launch is tracking to plan and which driver explains the gap.
- **S&OP & Long-Range Plan alignment views (Bridging the 24-month operational plan and 10-year LRP):** Side-by-side comparison views in RoadMap GPS 360 and enterprise BI show how changes in the near-term operational forecast impact years 1 through 10 of the portfolio long-range plan and capacity commitments. *Outcome:* Keep commercial, finance, and manufacturing leadership aligned on one horizon.
- **Forecast accuracy & bias reporting (Lag-1, Lag-3, and Lag-6 error scorecards):** Automated cycle-end reports score statistical baselines and consensus overrides across MAPE, MAD, RMSE, and directional bias by brand, strength, and channel at 1-, 3-, and 6-month lags. *Outcome:* Hold the forecasting process to an objective standard in every monthly review.
- **Expiry & batch coverage alerts (Remaining shelf life and weeks of cover):** Supply chain views combine lot-level inventory and minimum customer dating rules with the forward demand forecast to highlight lots at risk of expiry and markets approaching safety-stock thresholds. *Outcome:* Act on expiry risk and allocation needs months before they become write-offs or shortages.

#### Consumer Goods & Retail Applications
High-SKU consumer goods and retail teams cannot review thousands of items one by one. Automated exception dashboards and OLAP rollups surface the exact SKUs, accounts, and promotions that need attention right now.
- **Automated S&OP & IBP executive packs (Presentation-ready tables and charts on schedule):** We automate the weekly and monthly S&OP reporting pack, generating reconciled brand, category, and key-account tables alongside presentation-ready forecast charts and formatted Excel workbooks. *Outcome:* Reclaim days of analyst prep time every month and spend the meeting on decisions.
- **Forecast Value Added (FVA) scorecards (Measuring statistical baseline vs. planner & sales overrides):** Automated waterfalls compare the accuracy of the raw Geneva statistical baseline against planner adjustments, sales inputs, and executive consensus to show exactly which overrides reduced error and which added bias. *Outcome:* Focus planner effort on the exceptions where human judgment demonstrably beats the baseline.
- **OLAP drill-down from company to SKU (Interactive slice-and-dice across hierarchies):** Built on RoadMap GPS, GPS 360, or your BI platform (Power BI, Tableau, Looker), OLAP views let users drill seamlessly from total corporate revenue in dollars down to an individual SKU and distribution center in cases. *Outcome:* Answer leadership questions live in the meeting without going back to pull a new query.
- **Promotional performance & trade scorecards (Post-event baseline vs. incremental lift tracking):** As POS and shipment actuals arrive during and after a promotion, automated reports score incremental volume, cannibalization, and retailer/manufacturer margin against the pre-event what-if plan. *Outcome:* Know which events paid back their trade funding before locking next quarter's calendar.
- **Exception-based planner worklists (Top movers, bias streaks, and demand-sensing alerts):** Instead of paging through thousands of steady SKUs, planners receive a prioritized daily or weekly worklist of items whose actual orders or POS diverged significantly from the forecast interval. *Outcome:* Let planners manage 10x more SKUs by focusing only on true exceptions.
- **Inventory health & service-level dashboards (Fill rate, turns, weeks of supply, and E&O):** Unified supply views track order fill rate, inventory turns, weeks of cover, and excess and obsolete (E&O) stock by DC and product family against target safety-stock policies. *Outcome:* Keep working capital and customer service levels visible on the same screen.

#### Automated Reporting & Dashboards FAQs
- **What is Forecast Value Added (FVA) reporting?** Forecast Value Added compares the accuracy of the raw statistical baseline against each manual adjustment made by demand planners, sales, and leadership. Automated FVA scorecards show which overrides reduced forecast error and which introduced bias.
- **Can reports and S&OP packs be delivered automatically in native Excel as well as BI dashboards?** Yes. Alongside interactive views in RoadMap GPS 360, Power BI, or Tableau, our reporting pipelines generate formatted Excel workbooks (.xlsx) and PDFs with live formulas, charts, and pivot-ready tables on a daily, weekly, or monthly schedule.
- **How do exception alerts help planners manage large SKU catalogs?** Instead of reviewing thousands of items manually, automated threshold alerts flag only the SKUs or accounts where actual orders, POS velocity, or wholesaler weeks on hand breached the forecast confidence band or safety-stock target.
- **Can users drill down from executive totals to individual SKUs and customer accounts?** Yes. Multi-dimensional OLAP cubes and warehouse views let leadership view total company revenue in dollars and drill down in seconds to region, brand, customer banner, distribution center, and SKU in units or cases.

### Data Security & Privacy

- **URL:** https://roadmap-tech.com/data-services/data-security-privacy/
- **Summary:** HIPAA-aligned de-identification, tokenization, 2FA-hardened SFTP, and encryption that protect regulated data across every workflow.
- **Definition:** Data security and privacy services protect sensitive, proprietary, and regulated datasets while keeping them usable for forecasting and advanced analytics. RoadMap Technologies engineers HIPAA-aligned de-identification (Safe Harbor and Expert Determination), longitudinal patient tokenization, JSON clinical trial de-identification, two-factor authentication (2FA) across SFTP and planning systems, encryption in transit and at rest, and immutable audit trails.
- **Typical engagements:** De-identifying patient-level data via HIPAA Safe Harbor and Expert Determination; JSON-based de-identification for clinical trial and healthcare claims datasets; Deploying hardened SFTP servers with two-factor authentication (2FA) and encryption; Enforcing role-based access control, tokenization, and immutable audit trails

#### Life Sciences Applications
Life science analytics depends on patient-level claims, specialty pharmacy dispenses, hub enrollments, and clinical trial records. We engineer privacy and security controls directly into the ingestion and warehousing layer so your teams can model patient behavior without exposing protected health information (PHI).
- **HIPAA-aligned de-identification (Safe Harbor and Expert Determination workflows):** Automated pipelines strip or generalize all 18 HIPAA identifiers, apply geographic and age-band aggregation rules, and enforce small-cell suppression thresholds before patient records enter analytical tables. *Outcome:* Analyze patient-level demand drivers with documented HIPAA compliance built into the pipeline.
- **Longitudinal patient tokenization (Privacy-preserving patient linking across feeds):** Using cryptographic hashing and deterministic/probabilistic token matching, we link a patient's journey across specialty pharmacies, hubs, and medical/pharmacy claims without storing or exposing underlying PII or PHI. *Outcome:* Measure true persistency, adherence (PDC/MPR/DACON), and switching safely.
- **JSON clinical trial & claims de-identification (Structured nested-document redaction and masking):** Expanding on our JSON-based de-identification capabilities developed for FDA clinical trial and claims datasets, we parse, mask, and validate deeply nested JSON payloads while preserving schema integrity and clinical utility. *Outcome:* Prepare complex clinical and real-world evidence datasets for analysis and regulatory sharing.
- **Hardened SFTP with 2FA (Multi-factor authentication and chroot isolation):** All external data partner transfers run over dedicated SFTP servers enforcing two-factor authentication (SSH key + TOTP/MFA), strict IP allowlisting, chroot directory sandboxing, and automated PGP file encryption. *Outcome:* Eliminate unsecured file transfers across your specialty pharmacy and vendor network.
- **Role-based access & row-level security (Least-privilege governance across teams):** We configure role-based access control (RBAC) and row- or column-level security in your warehouse and RoadMap GPS 360 environment so users only see the brands, territories, and de-identified fields authorized for their role. *Outcome:* Share one central warehouse across commercial, medical, and finance with strict data boundaries.
- **Immutable audit trails & compliance evidence (Access logging, lineage, and security reviews):** Every file transfer, authentication event, de-identification run, schema change, and query against sensitive tables is written to tamper-evident audit logs, backed by our engineering team's experience achieving HITRUST r2 certification in 2022. *Outcome:* Pass vendor risk assessments and internal security audits with complete evidence on hand.

#### Consumer Goods & Retail Applications
Commercial price lists, unannounced product launches, retailer margin simulations, and M&A valuation models are among a company's most sensitive competitive assets. We protect your commercial and supply chain data across cloud, on-premises, and partner boundaries.
- **Sovereign on-premises or private-cloud deployment (Zero data egress when policy requires it):** For organizations that cannot send commercial or defense supply data to third-party SaaS clouds, RoadMap GPS, RoadMap GPS 360, and the Geneva Forecasting™ Engine deploy entirely on-premises or inside your virtual private cloud (VPC). *Outcome:* Run enterprise forecasting with 100% control over where your data resides.
- **Secure B2B partner file exchange (2FA-protected SFTP and encrypted APIs):** When exchanging POS actuals, order forecasts, or inventory balances with retail partners, 3PLs, and co-manufacturers, we enforce two-factor authentication, TLS 1.3 / SSHv2 transport, and PGP payload encryption. *Outcome:* Share CPFR and supply chain data with external partners without opening network vulnerabilities.
- **Commercial & pricing compartmentalization (Account- and margin-level access controls):** Row- and column-level security separates wholesale cost, manufacturing margin, and retailer-specific trade terms from general planning views, so planners see unit demand while finance and leadership see full P&L impact. *Outcome:* Collaborate on one S&OP plan without exposing sensitive margin or contract terms broadly.
- **Customer & household PII anonymization (Privacy-safe direct-to-consumer and loyalty analytics):** For ecommerce and omnichannel brands analyzing household trial, repeat, and cohort retention, our pipelines hash and tokenize customer identifiers, emails, and addresses before data lands in analytics marts. *Outcome:* Run household-level Parfitt-Collins and retention models without exposing consumer PII.
- **API key security & IP allowlisting (Scoped credentials for the Geneva Forecasting™ API):** Automated pipelines and internal apps connecting to the Geneva Forecasting™ API use scoped keys, configurable rate limits, IP allowlisting, and encrypted secret-vault rotation. *Outcome:* Embed automated forecasting into internal tools with enterprise-grade API governance.
- **Encryption & backup resilience (AES-256 at rest, TLS 1.3 in transit, and disaster recovery):** All planning databases, staging buckets, and forecast snapshots are encrypted at rest with AES-256 and backed up with point-in-time recovery and tested restore runbooks. *Outcome:* Protect the planning environment against data loss, ransomware, and accidental deletion.

#### Data Security & Privacy FAQs
- **What is data security & privacy?** Data security and privacy services protect sensitive, proprietary, and regulated datasets while keeping them usable for forecasting and advanced analytics. RoadMap Technologies engineers HIPAA-aligned de-identification (Safe Harbor and Expert Determination), longitudinal patient tokenization, JSON clinical trial de-identification, two-factor authentication (2FA) across SFTP and planning systems, encryption in transit and at rest, and immutable audit trails.
- **Which HIPAA de-identification methods do you implement?** We implement both HIPAA Safe Harbor (removing all 18 specified identifiers and generalizing dates and geography) and Expert Determination workflows, along with small-cell suppression and JSON-based de-identification for FDA clinical trial and healthcare claims datasets.
- **How does longitudinal patient tokenization work without exposing PHI?** Deterministic and probabilistic hashing generates an irreversible cryptographic token from patient attributes before records leave the secure landing zone, allowing analysts to link prescriptions, claims, and hub milestones for the same patient over time without storing names, SSNs, or dates of birth.
- **How are SFTP file transfers and database storage encrypted?** All file transfers run over SSHv2/SFTP with two-factor authentication or TLS 1.3 HTTPS, with PGP/GPG encryption on the files themselves. Data at rest in cloud or on-premises warehouses is encrypted with AES-256, protected by role-based access control and immutable audit logs.
- **Can RoadMap software and databases run entirely on-premises for data sovereignty?** Yes. RoadMap GPS, RoadMap GPS 360, and the Enterprise edition of the Geneva Forecasting™ API can be deployed 100% on-premises or inside your private cloud VPC so sensitive commercial, clinical, or defense data never leaves your network.

---

## Case Studies

Index URL: https://roadmap-tech.com/case-studies/

### Kraft Foods: trade promotion forecasting

- **URL:** https://roadmap-tech.com/case-studies/kraft-trade-promotion-forecasting/
- **Client:** Kraft Foods · **Industry:** Consumer packaged goods · **Scope:** Multi-account retail · Trade promotion
- **Summary:** Kraft Foods partnered with RoadMap Technologies to replace sales-driven overrides with statistical baseline forecasting, econometric promotional lift modeling, and retailer-level profit simulation across its trade planning process.
- **Key Takeaways:**
  - Baseline separation is foundational: Without statistically isolating everyday baseline velocity from promotional volume, every forecast either bakes past event spikes into the baseline or misattributes organic trend to trade spend.
  - Model lift from historical elasticity, not rules of thumb: Treating each promotion as a quantifiable econometric event across discount depth, duration, and merchandising execution replaces subjective sales assumptions with empirical volume projections.
  - Pre-event retailer profit simulation improves trade discipline: When both manufacturer contribution margin and retailer gross margin are visible before sign-off, unprofitable promotions are caught and restructured early.
  - Scenario modeling connects commercial intent to supply execution: Translating promotional what-if scenarios directly into time-phased ERP demand prevents event-driven stockouts, forward-buy whipsaws, and post-event excess inventory.

### Genentech: oncology and specialty therapy planning

- **URL:** https://roadmap-tech.com/case-studies/genentech-oncology-specialty-demand-planning/
- **Client:** Genentech · **Industry:** Life sciences · **Scope:** 0–24 mo. + 3–10 yr. · 3 therapy portfolios
- **Summary:** Genentech partnered with RoadMap Technologies to unify short-term operational demand forecasts with long-range strategic supply plans across oncology, neurology, and transplant anti-infective therapy portfolios, eliminating the planning disconnects that drove inventory imbalances and capital misallocation.
- **Key Takeaways:**
  - Short-term and long-range planning must share a single data foundation: When 0–24 month operational forecasts and 3–10 year strategic capacity plans run in separate silos, inventory buffers and capital investments inevitably drift out of alignment.
  - Specialty pharma portfolios demand therapy-specific statistical models: A single algorithm cannot capture oncology indication expansions and biosimilar erosion, chronic neurology persistency, and event-driven hospital transplant procurement simultaneously.
  - Override governance is as critical as statistical modeling: Measuring Forecast Value Added (FVA) and highlighting systematic manual override bias with stop-light indicators steadily raises organizational forecast discipline.
  - An S&OP/IBP cadence anchored in a unified baseline aligns the enterprise: Reconciling commercial ambition, manufacturing capacity, and financial outlook inside one hierarchical system eliminates costly cross-functional handoff friction.

### Johnson & Johnson: gross-to-net forecasting and reconciliation

- **URL:** https://roadmap-tech.com/case-studies/johnson-johnson-gross-to-net-forecasting/
- **Client:** Johnson & Johnson · **Industry:** Healthcare · **Scope:** Retail, hospital, specialty & govt. · GTN reconciliation
- **Summary:** Johnson & Johnson partnered with RoadMap Technologies to unify class-of-trade demand forecasting with Gross-to-Net financial reconciliation, closing the gap between supply chain planning and net revenue realization across its healthcare portfolio.
- **Key Takeaways:**
  - Aggregate forecast accuracy masks class-of-trade exposure: A top-line unit forecast that looks accurate at the national brand level can still trigger major earnings surprises if channel mix shifts toward higher-rebate government, 340B, or hospital contracts.
  - Gross-to-Net reconciliation belongs inside the forecasting workflow, not downstream of it: Embedding rebate, chargeback, and contract variance modeling directly into demand planning closes the lag between commercial volume commitments and net revenue accounting.
  - Shared forecasts between supply chain and finance elevate override discipline: When planners and commercial leads see both the Forecast Value Added (FVA) score and the immediate net revenue impact of a manual adjustment, speculative overrides drop sharply.
  - In global healthcare, demand forecasting is a core financial control: Unifying operational unit plans with GTN accrual logic protects both working capital on the supply side and balance-sheet reserve accuracy on the finance side.

### Samsung and Best Buy: collaborative retail replenishment

- **URL:** https://roadmap-tech.com/case-studies/samsung-best-buy-retail-replenishment/
- **Client:** Samsung × Best Buy · **Industry:** Consumer electronics and retail · **Scope:** CPFR framework · Best Buy (Fortune 100)
- **Summary:** Samsung implemented a Collaborative Planning, Forecasting and Replenishment (CPFR) framework with Best Buy in partnership with RoadMap Technologies, shifting from shipment-based forecasting to consumption-based planning and reducing supply chain volatility across high-revenue retail accounts.
- **Key Takeaways:**
  - Forecast consumer sell-through, not retail purchase orders: Anchoring supply plans in downstream point-of-sale (POS) consumption removes the batching lag and bullwhip distortion introduced by retailer replenishment orders.
  - CPFR is a strategic revenue protection framework: When a single Fortune 100 retail partner represents a concentrated share of category revenue, forecast misalignment directly threatens both top-line market share and gross margin.
  - Override discipline must be measured at SKU-location granularity: Tracking Forecast Value Added (FVA) across individual SKUs and distribution centers turns override governance from a policy guideline into an auditable performance metric.
  - Exception-based weekly reviews make joint planning scalable: Focusing weekly CPFR alignment meetings on high-variance SKUs and promotional windows rather than the entire catalog keeps cross-company teams decisive and sustainable.

### Enterprise Forecasting for Walmart

- **URL:** https://roadmap-tech.com/case-studies/walmart-home-entertainment-cluster-forecasting/
- **Client:** Walmart · **Industry:** Retail and home entertainment · **Scope:** Cluster-based demand planning & shelf space optimization
- **Summary:** At the peak of the home entertainment market, RoadMap Technologies partnered with Walmart to optimize shelf space allocation and replenishment across the Home Entertainment division using cluster-based demand forecasting and economic/demographic store segmentation.
- **Key Takeaways:**
  - Store clustering reduces forecast volatility: Grouping statistically similar stores by economic and demographic drivers amplifies true demand signals and removes individual store noise.
  - Economic and demographic signals drive localized assortment: Household income distribution, population density, and local media consumption patterns shape category elasticity far more than national averages.
  - Shelf space is a forecasting decision: Aligning linear footage and SKU depth with cluster-level demand elasticity outperforms static, one-size-fits-all planograms.
  - Forecast Value Added (FVA) governance protects accuracy at scale: Auditing manual overrides against cluster baselines ensures human adjustments only persist where they demonstrably improve outcomes.

### Dell, GE, and Samsung: forecasting in consumer electronics

- **URL:** https://roadmap-tech.com/case-studies/consumer-electronics-forecasting/
- **Client:** Dell, GE & Samsung · **Industry:** Consumer electronics · **Scope:** Lifecycle, price compression & installed-base service
- **Summary:** RoadMap partnered with leaders in consumer electronics, including Dell, GE, and Samsung, to address the sector's rapid product cycles, price compression curves, and multi-tier channel and service complexity.
- **Key Takeaways:**
  - In consumer electronics, forecasting precision translates directly into cash flow, gross margin, and market share: When hardware generations turn over every six months, even minor demand miscalculations leave behind obsolete inventory or missed launch windows.
  - Lifecycle planning requires continuous management of phase-in and phase-out transitions: Overlapping predecessor clearance and next-generation ramp curves must be modeled together rather than as isolated SKUs.
  - Average selling price (ASP) compression is a predictable curve, not a fixed constant: Modeling markdown progression from launch price through end-of-life clearance prevents teams from hitting unit volume targets while missing revenue and margin goals.
  - The true economic value of a device includes its installed-base ecosystem: Forecasting downstream accessories, replacement parts, consumables, and extended service contracts alongside hardware captures the full lifecycle P&L.
  - Hierarchical forecasting that mirrors multi-tier distribution is foundational: Aligning brand, product family, model generation, geography, sales channel, and end-user segment gives leadership one governed view of the portfolio.

### Media & entertainment: forecasting demand across release windows and subscriptions

- **URL:** https://roadmap-tech.com/case-studies/media-entertainment-demand-forecasting/
- **Client:** Media & entertainment · **Industry:** Media & entertainment · **Scope:** Releases, subscribers & multi-window channels
- **Summary:** RoadMap applied its launch and lifecycle forecasting methodology to media and entertainment businesses to handle demand that spikes on release, decays along reception curves, and spreads across physical, digital, licensing, and subscription channels.
- **Key Takeaways:**
  - In media and entertainment, the shape of demand matters as much as the total volume: Modeling the initial release spike and subsequent decay curve is the highest-leverage improvement teams can make over flat moving-average forecasts.
  - Distribution windows and channels cannibalize one another in predictable ways: Forecasting theatrical, physical, digital purchase, rental, streaming, and licensing windows separately prevents both launch-week shortages and post-window inventory waste.
  - For streaming and subscription businesses, the core unit of demand is the retained subscriber: Content release cadence acts as the primary causal lever on both subscriber acquisition spikes and post-finale churn.
  - Long-tail catalog demand sustains revenue between tentpole releases: Back-catalog titles, re-releases, and licensing windows deserve the same statistical rigor as premiere launches.
  - Hierarchical forecasting must mirror how content is monetized: Reconciling forecasts across title, format, distribution window, retail or digital channel, region, and audience cohort provides one unified portfolio view.

### Energy & utilities: forecasting load and consumption under weather-driven volatility

- **URL:** https://roadmap-tech.com/case-studies/energy-utilities-load-forecasting/
- **Client:** Energy & utilities · **Industry:** Energy & utilities · **Scope:** Load, weather & multi-horizon capacity
- **Summary:** RoadMap applied its econometric and time-series forecasting models to energy and utility operations, where consumption is driven by weather, seasonality, and long planning horizons, and where forecast error translates directly into grid reliability risk and capital cost.
- **Key Takeaways:**
  - In energy and utilities, forecast error carries direct grid reliability and capital consequences: Under-forecasting exposes operations to peak-event shortfalls and emergency spot purchases, while over-forecasting strands capital in underutilized generation and transmission assets.
  - Weather is a primary causal driver of load, not random noise: Explicitly modeling heating and cooling degree sensitivity is the highest-leverage improvement utility load planners can make.
  - Different planning horizons require distinct statistical structures: Unifying 15-minute/hourly dispatch, seasonal procurement, and multi-year infrastructure planning inside one coherent framework keeps operational and capital decisions aligned.
  - Structural baseline shifts must be isolated from short-term weather swings: Separating electrification growth, energy efficiency gains, and distributed solar adoption from cyclical weather volatility prevents costly long-range capacity surprises.
  - Hierarchical reconciliation across system, region, and customer class is foundational: Aligning residential, commercial, and industrial load curves with total system demand ensures both local distribution and system-wide resource adequacy.

---

## Published Articles

Index URL: https://roadmap-tech.com/blog/

### Forecasting 1 Million Time Series in Under 8 Minutes on a Single PC with Geneva Forecasting™ Engine

- **URL:** https://roadmap-tech.com/blog/forecasting-1-million-time-series-geneva-engine/
- **Published:** 2026-04-14 · **Category:** forecasting
- **Description:** Using RoadMap Technologies' Geneva Forecasting™ Engine API, we batch-forecasted 1 million time series in 7 minutes and 9 seconds at a rate of 2,300 to 2,500 series per second on a single $2,000 desktop PC with no GPU.
- **Key Takeaways:**
  - The C++ Geneva Forecasting™ Engine API forecasted 1 million time series from the M4 Competition dataset in 7 minutes and 9 seconds (2,300 to 2,500 series per second) on a single desktop PC.
  - Because Geneva is a deterministic, CPU-native C++ engine, it requires no GPU hardware or expensive cloud GPU instances to run enterprise-scale batch workloads.
  - Self-hosted and on-premises deployments give engineering and planning teams full control over hardware utilization, reproducibility, and cloud costs.

### Why Pharmaceutical Market Access is Dependent on Risk Sharing and Persistency Modeling

- **URL:** https://roadmap-tech.com/blog/pharmaceutical-market-access-risk-sharing-persistency-modeling/
- **Published:** 2025-06-18 · **Category:** life-sciences
- **Description:** In our case study for an injectable migraine medication, a higher patient persistency curve for patients with a lower co-pay increased drug utilization by 20%, while lowering payor price by 26% and payor total cost by 11%.
- **Key Takeaways:**
  - Traditional high co-pays and prior authorizations restrict market access and cause middle- and lower-income patients to abandon effective specialty therapies.
  - Risk-sharing programs pair prescribed starter samples with co-pay assistance ($5 to $30 per month) to remove upfront financial and administrative barriers.
  - In our injectable migraine case study, modeling the patient persistency curve at a lower co-pay increased utilization by 20% while reducing payor price by 26% and total payor cost by 11%.

### Product Life Cycle Curves in the 21st Century

- **URL:** https://roadmap-tech.com/blog/product-life-cycle-curves-21st-century/
- **Published:** 2024-09-10 · **Category:** forecasting
- **Description:** Savvy consumers, preorders, and social media have compressed the classic innovation curve into the initial launch month. Here is a three-step framework for forecasting products with short life cycles.
- **Key Takeaways:**
  - Preorders and social media have compressed the innovator phase of the classic product life cycle into the launch month, making month one the peak sales month for many high-tech products.
  - Accurate short-lifecycle forecasting requires combining three years of predecessor sales history with customer-facing product attributes and technology roadmaps.
  - Comparing full-lifecycle statistical forecasts against sales force initial order estimates provides a critical sanity check before disaggregating plans into weekly execution buckets.