Demand Intelligence
What will we need, and how far can we trust the forecast?
Forecasts demand for every item at every location over a twelve-week horizon, and proves the method before asking anyone to rely on it. Each forecast is tested against weeks that were held back, so the page shows demand against the holdout, the error (WAPE) and a forecast range for the next twelve weeks.
- Twelve-week forecast with a stated range
- Holdout test: demand against forecast, with WAPE and bias
- Performance by item and location
- Seasonality and demand drivers in view
- What-if on demand, lead time and service policy
- Duration: 4–6 weeks for an outcome-based POC
How the AI works. Forecasting models predict demand for every item and location over twelve weeks and are tested against weeks that were held back before anyone relies on them, with the error (WAPE), bias and forecast range shown openly. Planners see where the AI forecast is strong and where it is not, and the what-if carries the forecast straight into a stocking decision.
Model performance is shown by item and location, so planners can see where the forecast is strong and where it is not. Demand Forecasting sits beside Inventory Health and Replenishment, so a forecast leads directly into a stocking decision.
The predictive what-if changes demand, lead time, service policy or review interval and shows the result across 48 item and location combinations.