How can logistics and operations teams better optimize the plans generated by decision models through streamlining the incorporation of machine learning outputs such as forecasts? Through better ML/OR connections!
What if optimization and decision science teams could better fit multiple ML models to better explain the relationship between decision model variables? What if that could enable teams to choose the best among the ML models to then apply to the optimization step?
In this techtalk, join Nextmv CTO Ryan O’Neil for an overview of blending ML and OR, a demonstration using Gurobi’s avocado price optimization example, and time for Q&A at the end. Ryan will also show switching between multiple trained scikit-learn estimators, including linear regression, decision trees, gradient boosting, and random forests.
Key takeaways
- Nextmv ML/OR connector overview
- ML/OR connector speedrun (Gurobi price optimization example, Gurobi ML, Gurobipy Pandas, scikit-learn)
- Time for Q&A
Get started on Nextmv for free and learn more in the documentation.
Have questions? Reach out to us to talk with our technical team
