Presented by Vijay Pappu, Senior ML Engineering Manager, Personalization Lead at Peloton, this talk focuses on any ML systems that rely on a feedback loop for improvement. How do we measure the efficacy of an ML system? Improving ML models offline beyond the first A/B test can be achieved in several ways: feature engineering, complex models, larger datasets. He also shares that cohort analysis could potentially improve online metrics and more.
Sign up for the free insideAI News newsletter.
Join us on Twitter: @InsideBigData1 – https://twitter.com/InsideBigData1
