Pricing and Promotion Decision Engine

A live, end-to-end pricing decision tool built on 6.6 million rows of Dominick’s Finer Foods scanner data (cleaned panel of 4.65 million rows, covering 486 UPCs, 93 stores, and 366 weeks). Translates academic counterfactual-simulation workflow into product-level pricing decisions.

🚀 Launch the Live App

💻 View Source Code on GitHub

The observational demand estimates support conditional pricing scenarios. A/B tests are planned validation steps; simulated profit changes are not measured business outcomes.

What it does

• Estimate behavioral response: log-log fixed-effects demand model with Duan smearing retransformation to reduce log-to-level retransformation bias.
• Simulate counterfactuals: price and promotion counterfactual simulations over the estimated demand system.
• Optimize under constraints: constrained profit optimization under cost, inventory, and margin limits; A/B validation plans with power analysis before any candidate action ships.
• Ship: deployed as an interactive Streamlit application backed by a modular Python codebase, a pytest test suite, reproducible requirements, and auto-deploy from GitHub.

Stack

Python (pandas, statsmodels, scikit-learn), Streamlit, pytest, Git/GitHub.

Narrative

The workflow — estimate → simulate → optimize — mirrors the research-to-decision pipeline I use in my regional trade and market-integration research. The unit of analysis shifts from regions to firms, while assumptions and validation requirements depend on the setting.