Classical Machine Learning
Repair what the first model missed
A journey through gradient boosting with Botie.
Classical Machine Learning · A journey with Botie
First visit? Learn the workshop controlsBotie's notebook
Could the Next Model Concentrate on What We Got Wrong?
Part 1 of 3
Suppose a simple model captures the broad pattern but consistently predicts too low in one region and too high in another. We could throw it away and start over. Or we could keep what it learned and ask another small model to describe the corrections it still needs.