Revisit feature engineering when data drift impacts performance, typically every 3–6 months (or sooner if metrics drop).

Key indicators:

• Model performance decay (e.g., dropping accuracy/F1 score).

• Statistical drift (KS test, PCA, or feature distribution shifts).

• Domain shifts (e.g., policy changes, new user behavior).

Monitoring: Track input feature stats (mean, variance) and set alerts for anomalies. Retrain if drift exceeds thresholds.

Rule: Update features only if drift harms results—don’t fix what isn’t broken.