Speaker:: Emeli Dral
Track: PyData: Machine Learning & Stats
When your ML model is in production, you might observe input data and prediction drift. In absence of ground truth, drift can serve as a proxy for the model performance. But how exactly to evaluate it? In this talk, I will give an overview of the possible approaches, and how to implement and visualize the results.
Recorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022.
[ Ссылка ]
More details at the conference page: [ Ссылка ]
Twitter: [ Ссылка ]
Twitter: [ Ссылка ]
Ещё видео!