Enterprise Retail & supply chain
Warehouse Forecasting
Solution Architect & MLOps · H-E-B
Forecasts of outbound and pallet selection for 12 distribution centers, used to plan labor and transportation a month ahead.
- WMAPE, flat across 28 days
- 9.05%
- distribution centers
- 12
- forecast–actual pairs monitored
- 2.2M
The problem
Distribution centers plan labor and trucks weeks in advance; forecasts had to be accurate across the full horizon and monitored continuously.
What I built and led
- Architected and productionized a Databricks/Spark system on AWS forecasting outbound and pallet selection for 12 distribution centers over a 28-day horizon, with per-series XGBoost models, MLflow tracking, weekly retraining and daily scoring.
- Built Spark-native accuracy monitoring over 2.2 million forecast–actual pairs, and shipped v2 as a zero-downtime shadow deployment.
Results
- 9.05% WMAPE, flat across 28 days
- 12 distribution centers
- 2.2M forecast–actual pairs monitored