Data Drift Detection in Production ML: Population Stability Index (PSI) & Monitoring

Calculating Population Stability Index (PSI)

PSI measures how much a feature distribution in production serving data has shifted relative to baseline training data:

# PSI Formula Concept
PSI = sum( (Actual_i - Expected_i) * ln(Actual_i / Expected_i) )

A PSI > 0.2 indicates significant distribution drift, triggering automated retraining pipelines.

References & Further Reading:

• Evidently AI ML Monitoring Documentation