Completed
Defining Failure as an SLA Breach and What We Can Do About It
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Stop Failures Before They Happen - Gradient Boosting for Workflow Risk Prediction
Automatically move to the next video in the Classroom when playback concludes
- 1 The Pain: Long Workflows That Fail Late
- 2 Why Prefect Is the Perfect Place for Early Signals
- 3 Defining Failure as an SLA Breach and What We Can Do About It
- 4 Case Study: Portfolio Risk Flow & Early Feature Signals
- 5 Modeling Approach: CatBoost, Baselines, and Evaluation
- 6 Explaining Risk: SHAP Drivers Developers Can Act On
- 7 Live Demo in Prefect UI: Low-Risk Run vs High-Risk Run
- 8 From Demo to Production: Code Changes, Safe Rollout, and Drift Monitoring
- 9 Beyond SLAs: Rerouting, Smarter Retries, and the Big Takeaway
- 10 Wrap-Up and Thanks
