Performance Decay Once Labels Arrive: Precision, Recall & an AUC Proxy
This lesson is part of the course
In this lesson
You calculate precision, recall and balanced accuracy for six monthly cohorts whose default labels have arrived, and measure how far June has fallen below the validation result.
Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.
Lessons in this course
- Baseline vs Current: Binning a Feature with COUNTIFS & FREQUENCY Locked
- Population Stability Index (PSI) per Feature, with Thresholds Locked
- Kolmogorov–Smirnov: Cumulative Distributions & the Largest Gap (with a Chart) Locked
- Categorical Drift: Chi-Square Test & Jensen–Shannon Divergence Locked
- Prediction Drift: The Score Distribution Month by Month (with a Chart) Locked
- Performance Decay Once Labels Arrive: Precision, Recall & an AUC Proxy Locked
- Alert Rules & a Monitoring Dashboard with Traffic Lights Locked
- The Retraining Decision: Cost of Drift vs Cost of Retraining Locked