15How do you detect data drift and concept drift in production, concretely?▼medium★ EssentialDatabricksMicrosoftAmazon2 replies○ sign inModels decay silently as the world shifts, and 'monitor for drift' is too vague. The signal is the actual statistical methods and distinguishing data drift you can detect without labels from concept drift you often cannot.Open full answer →
47PSI, KL divergence, MMD, and the KS test all detect drift. When do you reach for each?▼hardDatabricksMicrosoftAmazon2 replies◆ premiumFour drift tests, four different assumptions. The weak answer lists them; the strong one knows which handles high-dimensional embeddings, which needs binning, and which gives a calibrated p-value. Here is how to choose.Open full answer →
