Demand Intelligence
What will repair jobs and routine work consume?
Forecasts recurring consumption of repair materials, service kits and spares at item cost, and adds confirmed and planned job requirements once. In the sample, weekly recurring consumption is about S$67.5k and the model is tested on a six-week rolling backtest against a last-week baseline.
- Recurring forecast per week at item cost
- Rolling backtest against a baseline
- Known job requirements added separately
- Forecast bias and error shown
- 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.
Four yards and 32 item-yard pools are planned over an eight-week horizon.