MS Interpret - Fit interpretable models. Explain blackbox ML

InterpretML is an open-source python package for training interpretable models and explaining blackbox systems. Interpretability is essential for:

Model debugging - Why did my model make this mistake? Detecting bias - Does my model discriminate? Human-AI cooperation - How can I understand and trust the model’s decisions? Regulatory compliance - Does my model satisfy legal requirements? High-risk applications - Healthcare, finance, judicial, …

For more details, visit the source.