Price Optimization with Competing Products

Unlock the power of data-driven pricing optimization for your business in retail, e-commerce, ticketing, and hospitality industries. Striking the right balance between price and demand is a challenge, but data scientists have made significant strides. However, a crucial piece is often overlooked—making the ideal pricing decision while navigating various constraints and business rules.

Imagine having a product with multiple categories but limited space—whether it’s shelf space in retail, event seats, or hotel rooms. This is where our solution comes into play. We tackle the challenge of optimizing the mix of products within a constrained space and maximizing revenue while adhering to business rules.

This modeling example involves creating a predictive model to forecast sales based on product prices, then we build an optimization model to identify the optimal product mix. Leveraging the Gurobi-sponsored open-source package Gurobi Machine Learning, we seamlessly integrate machine learning features with decision-making in the optimization model.

This modeling tutorial is at the beginner level, where we assume that you know Python and that you have a background in a discipline that uses quantitative methods.

You may find it helpful to refer to the documentation of the Gurobi Python API.