Tag: retraining
-
Retraining strategy with evolving classes + imbalanced labels?
Retraining strategy with evolving classes + imbalanced labels? Hi all — I’m looking for advice on the best retraining strategy for a multi-class classifier in a setting where the label space can evolve. Right now I have about 6 labels, but I don’t know how many will show up over time, and some labels appear…
-
Stop Retraining Blindly: Use PSI to Build a Smarter Monitoring Pipeline
Stop Retraining Blindly: Use PSI to Build a Smarter Monitoring Pipeline A data scientist’s guide to population stability index (PSI) The post Stop Retraining Blindly: Use PSI to Build a Smarter Monitoring Pipeline appeared first on Towards Data Science. Gustavo Santos Go to original source
-
The Misconception of Retraining: Why Model Refresh Isn’t Always the Fix
The Misconception of Retraining: Why Model Refresh Isn’t Always the Fix Retraining is easy; knowing when not to is the real challenge. In machine learning, performance drops are rarely about stale weights; they’re about misunderstood signals. The post The Misconception of Retraining: Why Model Refresh Isn’t Always the Fix appeared first on Towards Data Science.…