Switchback testing for decision models allows algorithm teams to compare a candidate model to a baseline model in a true production environment, where both models are making real-world decisions for the operation.
Learn more:
https://doordash.engineering/2019/02/20/experiment-rigor-for-switchback-experiment-analysis/
Learn how to solve mixed integer programming (MIP) problems with Google’s OR-Tools for use cases like scheduling, order fulfillment, packing and more. Then promote an updated model to production using CI/CD.
Four decision algorithms, multiple experiments, one platform. Explore recently released batch testing capabilities for evaluating model changes to compare output metrics, KPIs, and prepare for acceptance and scenario tests.
How do you feel about the decision model updates you ship to production? Acceptance and shadow testing are two ways to gain confidence across model performance for business KPIs and stability indicators. We’ll show you how.
