Inventory forecast and reorder points

The brief

Warehouses either run out or overstock because they order by habit. Forecast weekly demand per product, then set reorder points and safety stock from the forecast error, and show the trade-off between stock-outs and stock held. Good looks like: forecasts that beat a moving average, back-testing, and reorder points tied to a service level.

What you will build

1. Build weekly demand series per product
2. Compare moving-average and gradient-boosted forecasts
3. Back-test over several months
4. Set safety stock and reorder points for a service level
5. Show stock-out versus holding cost

Free, open data to build it with

• M5 forecasting (Walmart) ↗ Kaggle

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.