Data scientists: what's your team's approach to tracking the quality of models in production?
(How do you know if a model is decaying? How do you quality-check the data going into a model? Who builds and tracks these things?)
(How do you know if a model is decaying? How do you quality-check the data going into a model? Who builds and tracks these things?)
Would love your thoughts (and any talk recommendations!), @chrisalbon @jonathonmorgan @therriaultphd @RandiRLudwig @math_rachel @tdhopper @randal_olson @drob @ledell
Woo, this thread really took off, and I realized I never shared a summary document that I created to categorize all of the advice therein. Here's the doc, in case it's useful for anyone: docs.google.com/document/d/1Qw…
