Module 08
Data Quality & Monitoring
Validate, monitor, and debug data and ML pipelines before bad data reaches models or users.
7 lessons · 4 videos · 1h 20m- 08.01
Data Quality Dimensions
Define measurable checks for freshness, completeness, validity, uniqueness, consistency, accuracy, and distribution stability.
- 08.02
Great Expectations Validation
Create a Great Expectations suite that validates schema, null rates, ranges, categorical values, and row counts.
- 08.03
Contract Tests for Pipelines
Write producer-consumer data contract tests that catch breaking schema and semantic changes before deployment.
- 08.04
Data Drift Detection
Calculate feature drift metrics such as PSI, KL divergence, and distribution summary changes on production data.
- 08.05
Label and Concept Drift
Distinguish feature drift, label drift, and concept drift and select monitoring signals for each.
- 08.06
ML Observability Dashboards
Design a dashboard that tracks data freshness, feature distributions, prediction distributions, latency, and model performance.
- 08.07
Incident Response for Data Pipelines
Create a runbook for triaging a data quality incident from alert to rollback, replay, or downstream notification.