0Pricing
Data Science Academy · Lesson

Why Accuracy Lies on Imbalance

The rare-class trap.

The Comfortable Lie

Accuracy feels like the obvious score: how many predictions you got right. On balanced data it works fine, but imbalance quietly breaks it.

What Imbalance Means

A dataset is imbalanced when one class is far rarer than the others. Think fraud, disease, or churn: the interesting event is the rare one.

All lessons in this course

  1. Why Accuracy Lies on Imbalance
  2. Resampling: SMOTE and Undersampling
  3. Class Weights and Thresholds
  4. Pick Metrics for Rare Events
← Back to Data Science Academy