$1.2M saved/yearData Science
Supply Chain Optimization
Demand forecasting and inventory optimization across multi-warehouse e-commerce with 10K+ SKUs.
$1.2M
Annual Savings
10K+
SKUs
98.5%
Service Level
40%
Less Overstock
The Challenge
10K+ SKUs with seasonal patterns, promotions, and supply disruptions across 8 warehouses.
The Solution
1
Hierarchical Prophet — top-down/bottom-up reconciled
2
Promotional lift modeling from historical campaigns
3
Linear programming via PuLP for 8-warehouse allocation
4
Safety stock optimization per SKU
// Tech Stack
Built With
Python
Prophet
PuLP
Snowflake
Streamlit
Docker
Pandas
Airflow
// Results
Impact
$1.2M savings annually. 40% less overstock. 98.5% service levels. Runs daily automatically.
// More