Model Evaluation Metrics

Pick, compute and defend the right metric for classification, regression and ranking

Master the confusion matrix and its derived metrics, ROC vs precision-recall curves, log loss, calibration and ECE, cost-based threshold selection, regression and ranking metrics like NDCG, multiclass averaging, and how to tell real metric gains from noise.

Practice questions (7)

• Reading a Confusion Matrix Under Imbalance

  Intermediate · Free
  View →

• ROC-AUC vs PR-AUC for a Rare-Event Model

  Intermediate
  View →

• Choosing a Threshold From a Cost Matrix

  Intermediate
  View →

• Diagnosing Calibration From a Reliability Table

  Advanced
  View →

• Comparing Two Rankers With NDCG and MRR

  Advanced
  View →

Quizzes (1)