Guides
ML Evaluation Playbook
How to know whether your model is actually any good.
The metrics, splits and sanity checks that separate a model you can deploy from one that merely scores well. Covers imbalanced classification properly, leakage patterns that inflate results, threshold tuning, and how to report findings to people who will make decisions based on them.
What is inside
- Metric selection by problem type, and why accuracy is usually the wrong answer
- The leakage catalogue: resampling, scaling and feature engineering done in the wrong order
- Threshold tuning as a first-class step rather than an afterthought
- Cross-validation schemes for grouped, temporal and imbalanced data
- Reporting templates for communicating uncertainty to non-technical stakeholders
- Notebook companions for every chapter, runnable end to end
Built with
- Python
- scikit-learn
- imbalanced-learn
- Jupyter
Next step
Have an AI problem worth solving?
Tell me what you are trying to build. I will tell you honestly whether AI is the right tool, what it would take, and how I would approach it.
Typical reply within 24 hours
Working from Dhaka, Bangladesh · remote worldwide