385: Advanced Data Topics and People-Centered Data Science
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
How to Monitor a Production AI or Machine Learning Model
Model drift is kind of a silly name, but basically it means that the performance is going to drift over time. All models tend to decay over time and different models decay at different rates. Plan for outs of lessons before you put the first model in. Second thing is I use what's called a population stability report which sounds like some sort of bizarre sociology experiment. You definitely need to retrain your model in that the world that the model is trying to represent has changed.
Play episode from 32:05
Transcript
