data-portfolio

← Portfolio · Notebook


Hierarchical Retail Demand Forecasting — M5

Business question

Produce coherent SKU × store × week forecasts — a category forecast must equal the sum of its SKUs — to plan shelf replenishment and department buying off the same numbers.

Data & EDA

Modeling

Level Approach
Aggregate (state, department) SARIMA / Prophet / ETS
Base (SKU × store) LightGBM with rich lag, rolling, price, calendar features
Reconciliation MinT (minimum-trace) optimal combination across hierarchy

Validation

Deployment

Business outcome