Topic: Retail
Retail AI earns most of its value in assortment
Forecasting and replenishment get the attention. The larger and less contested gain is deciding what to carry, where, and what to stop carrying.
Store-level decisions need store-level context
The model sees a store as a set of sales figures. The manager sees a car park, a school run and a competitor that opened in March.
Inventory optimisation across a network is a different problem
Optimising each location independently produces a network that is simultaneously overstocked and out of stock.
What an agent needs to know before it can price anything
Elasticity is the easy part. The hard part is the list of prices you are not allowed to set, and why.
The stockout you can predict is not the one that hurts
Regular demand is easy to forecast and rarely causes stockouts. The damage comes from the events your model has three examples of.
Assortment decisions are where retail AI earns its keep
Replenishment optimises what you already sell. Assortment decides what you sell. One of these has an order of magnitude more upside.
Retail replenishment is a decision problem wearing a forecasting costume
Every replenishment system forecasts demand and then applies a rule. The forecast gets the investment. The rule decides the outcome.