Demand Forecasting for a 200-Order Kitchen: What Big-Company Models Get Wrong
Why ARIMA and Prophet underperform your gut below a certain data volume. What actually worked: a quantile-regression baseline plus a weather-and-weekend correction.
Small-business data lessons — forecasting, inventory, calibration — from running a 200-order-a-week kitchen. Written for operators without a data team.
Why ARIMA and Prophet underperform your gut below a certain data volume. What actually worked: a quantile-regression baseline plus a weather-and-weekend correction.
Treating every par-level as a probabilistic forecast with an explicit service-level target cut our chicken-filling waste by ~18%. Math and a spreadsheet.
“We’ll do $40k next month” is a wish, not a plan. Three steps to calibrated ranges any owner can run in a spreadsheet.