X-SHAP: towards multiplicative explainability of Machine Learning [article]

Luisa Bouneder, Yannick Léo, Aimé Lachapelle
2020 arXiv   pre-print
This paper introduces X-SHAP, a model-agnostic method that assesses multiplicative contributions of variables for both local and global predictions. This method theoretically and operationally extends the so-called additive SHAP approach. It proves useful underlying multiplicative interactions of factors, typically arising in sectors where Generalized Linear Models are traditionally used, such as in insurance or biology. We test the method on various datasets and propose a set of techniques
more » ... d on individual X-SHAP contributions to build aggregated multiplicative contributions and to capture multiplicative feature importance, that we compare to traditional techniques.
arXiv:2006.04574v2 fatcat:34wyu6am55fx3lz6pdhqe5dzua