Supply Optimization at Instacart

Instacart uses a large network of personal shoppers and delivery drivers to shop for all the groceries customers order and deliver them within their due window. On any given day, it becomes extremely critical to figure out how many shoppers and drivers we need to staff so as to adequately meet all the demand. But this is easier said than done as on a day-to-day basis, there are multiple factors that contribute to a large amount of variance. This talk explores a novel simulation-based optimization methodology that we employed to staff our shoppers and drivers, so as to maximize efficiency, minimize idle shopper hours and minimize orders lost due to lack of supply, all while managing the uncertainty.