Discussion on "Episode 16: Phase 5: LightGBM Didn't Win the Way I Expected. It Won Differently."

Aditya Dandia · 2026-04-26T12:27:18.041Z

Act 1 — The Setup Phase 4 ended with LR + SMOTE as the model to beat. Churn recall of 0.80. ROC-AUC of 0.839. A logistic regression — the simplest model in the toolkit — holding the top spot after fou

Discussion on "Episode 16: Phase 5: LightGBM Didn't Win the Way I Expected. It Won Differently." | Hashnode

Search Hashnode

Episode 16: Phase 5: LightGBM Didn't Win the Way I Expected. It Won Differently.

Responses