From retail warehousing to airline ticketing, data scientists and decision scientists alike are building models to understand the relationship between price and demand. As more business rules and constraints are added, the interaction becomes more complex, making the need for optimization greater. Gurobi’s Price Optimization with Competing Products notebook walks through two models to address this problem: a predictive model to forecast sales based on price and an optimization model to find the optimal mix of products. It also uses Gurobi Machine Learning to integrate the regression model into the optimization model.
Once we’ve run through the notebook, we’ll take the next step to operationalize it with Nextmv. In a few lines of code, the model can be called via an API and now has a system of record for model code updates, run history, and more. Your teammates can share custom visualizations, access the same input data, and test how the model will perform under different conditions. In this 30-minute talk, we’ll push the models from the Gurobi notebook to Nextmv, create a decision workflow (or optimization pipeline), and perform a scenario test.
Key takeaways
- Overview of the Gurobi notebook for price optimization with competing products
- Pushing a Gurobi notebook to Nextmv
- Creating and managing decision workflows
- Rendering custom visualizations
- Performing a scenario test
Get started on Nextmv for free and learn more in the documentation.
Have questions? Reach out to us to talk with our technical team.
.png)
