This project applies data science and operations research techniques to optimize product pricing and inventory management using real-world datasets. The goal is to simulate the decision-making pipeline for a retail business — from setting prices to managing stock — while maximizing revenue and minimizing cost.
Retailers face the challenge of setting competitive prices while ensuring sufficient stock availability. Poor pricing can reduce revenue, and bad inventory planning can lead to lost sales or excess holding costs. This project tackles these core challenges using:
- Price elasticity modeling
- Time-series demand forecasting
- Inventory policy simulation
-
Price Optimization
Estimate price elasticity and simulate revenue-maximizing price points. -
Demand Forecasting
Forecast future demand using SARIMA and Prophet models. -
Inventory Optimization
Recommend inventory levels using EOQ, safety stock models, and SKU segmentation. -
Inventory Classification
Segment SKUs by value (ABC) and predictability (XYZ) for differentiated policies.
priceWise/
├── data/ # Raw and processed datasets
├── notebooks/ # Jupyter notebooks for each stage
├── src/ # Python modules for reuse
├── reports/ # Summary markdown and generated visuals
├── requirements.txt
└── README.md