With Gurobi Machine Learning—an open-source Python project to embed trained machine learning models directly into Gurobi—data scientists can more easily tap into the power of mathematical optimization.

Specifically, Gurobi Machine Learning allows users to add a trained machine learning model as a constraint to a Gurobi model (e.g., from scikit-learn, TensorFlow/Keras, or PyTorch). Thus, you can estimate a real-world system by training a machine learning model, and then use the machine learning model as a constraint in Gurobi, so you can optimize controls on that system.

In recent years, machine learning has become a prevalent tool to provide predictive models in many applications. In this talk, we are interested in using such predictors to model relationships between variables of an optimization model in Gurobi.

For example, a regression model may predict the demand of certain products as a function of their prices and marketing budgets, among other features. We are interested in being able to build optimization models that embed the regression so that the inputs of the regression are decision variables, and the predicted demand can be satisfied.