SHAP
Contents
SHAP¶
SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions (see papers for details and citations).
Resources
SHAP at Paypal¶
How do ML models use their features to make predictions? SHAP opens up the ML black box by providing feature attributions for every prediction of every model. Being a relatively new method, SHAP is gaining popularity extremely quickly thanks to its user-friendly API and theoretical guarantees.
In this talk you will will gain intuition about what SHAP is based on and how SHAP values can be aggregated to understand model behavior.
About the speaker: Adi is a data scientist at PayPal, developing Machine Learning models for fraud detection.