‍

‍

You’ve developed your pipeline and Bodywork has made easy work of deploying it. But, the job does not finish here - your models are in-production, in-the-wild, but trained on data from a different point-in-time. The world changes quickly and you need to monitor model output to ensure that scores based on historical data are still relevant today.

Monitoring models for drift and degradation is not easy - theoretically or practically. In this example project we show how to outsource these problems to Aporia’s model monitoring platform, by using their Python client from within a Bodywork pipeline.