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 insideBIGDATA newsletter.
Join us on Twitter: @InsideBigData1 – https://twitter.com/InsideBigData1
Speak Your Mind