shapr

Prediction Explanation with Dependence-Aware Shapley Values

Complex machine learning models are often hard to interpret. However, in many situations it is crucial to understand and explain why a model made a specific prediction. Shapley values is the only method for such prediction explanation framework with a solid theoretical foundation. Previously known methods for estimating the Shapley values do, however, assume feature independence. This package implements the method described in Aas, Jullum and Løland (2019) <arXiv:1903.10464>, which accounts for any feature dependence, and thereby produces more accurate estimates of the true Shapley values.

Version History