X-SHAP: towards multiplicative explainability of Machine Learning

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 based on individual X-SHAP contributions to build aggregated multiplicative contributions and to capture multiplicative feature importance, that we compare to traditional techniques.

[1]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[2]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[3]  Olaf Gefeller,et al.  A Multiplicative Variant of the Shapley Value for Factorizing the Risk of Disease , 2000 .

[4]  David A. Landgrebe,et al.  A survey of decision tree classifier methodology , 1991, IEEE Trans. Syst. Man Cybern..

[5]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[6]  Tommi S. Jaakkola,et al.  On the Robustness of Interpretability Methods , 2018, ArXiv.

[7]  Hugh Chen,et al.  From local explanations to global understanding with explainable AI for trees , 2020, Nature Machine Intelligence.

[8]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[9]  Daniel Gómez,et al.  Polynomial calculation of the Shapley value based on sampling , 2009, Comput. Oper. Res..

[10]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[11]  Erik Strumbelj,et al.  Explaining prediction models and individual predictions with feature contributions , 2014, Knowledge and Information Systems.

[12]  K. Michael Ortmann.  A cooperative value in a multiplicative model , 2013, Central Eur. J. Oper. Res..

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  H. Young.  Monotonic solutions of cooperative games , 1985 .

[15]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[16]  L. Shapley.  A Value for n-person Games , 1988 .

[17]  S. Preston,et al.  Are major behavioral and sociodemographic risk factors for mortality additive or multiplicative in their effects? , 2016, Social science & medicine.

[18]  Alexander J. McNeil,et al.  Bayesian inference for generalized linear mixed models of portfolio credit risk , 2007 .

[19]  Bin Su,et al.  Multiplicative structural decomposition analysis of energy and emission intensities: Some methodological issues , 2017 .

[20]  J. Beirlant,et al.  Actuarial statistics with generalized linear mixed models , 2007 .

[21]  Yair Zick,et al.  Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems , 2016, 2016 IEEE Symposium on Security and Privacy (SP).