AI in the Real World Section 105
Retail, Demand and Supply Chain
Forecasting things you sell and moving them to people — where the forecast is only useful if it turns into a decision.
12 of 12 lessons published Three reading levels on every lesson
Lessons in order
Work top to bottom. Each lesson assumes the one above it.
- Retail demand data
- You measure sales, not demand
- Intermittent demand and mostly-zero series
- Making store, region and national forecasts add up
- Turning a forecast into an order quantity
- Promotions, cannibalisation and halo
- Price elasticity and dynamic pricing
- Forecasting a product with no history
- Predict then optimise
- Predicting arrival times
- Snapping noisy GPS to roads
- Messy addresses and geocoding