%0 Conference Proceedings
%T Explaining Predictive Models with Mixed Features Using Shapley Values and Conditional Inference Trees
%+ Norwegian Computing Center (NR)
%A Redelmeier, Annabelle
%A Jullum, Martin
%A Aas, Kjersti
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE)
%C Dublin, Ireland
%Y Andreas Holzinger
%Y Peter Kieseberg
%Y A Min Tjoa
%Y Edgar Weippl
%I Springer International Publishing
%3 Machine Learning and Knowledge Extraction
%V LNCS-12279
%P 117-137
%8 2020-08-25
%D 2020
%R 10.1007/978-3-030-57321-8_7
%K Explainable AI
%K Shapley values
%K Conditional inference trees
%K Feature dependence
%K Prediction explanation
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X It is becoming increasingly important to explain complex, black-box machine learning models. Although there is an expanding literature on this topic, Shapley values stand out as a sound method to explain predictions from any type of machine learning model. The original development of Shapley values for prediction explanation relied on the assumption that the features being described were independent. This methodology was then extended to explain dependent features with an underlying continuous distribution. In this paper, we propose a method to explain mixed (i.e. continuous, discrete, ordinal, and categorical) dependent features by modeling the dependence structure of the features using conditional inference trees. We demonstrate our proposed method against the current industry standards in various simulation studies and find that our method often outperforms the other approaches. Finally, we apply our method to a real financial data set used in the 2018 FICO Explainable Machine Learning Challenge and show how our explanations compare to the FICO challenge Recognition Award winning team.
%G English
%Z TC 5
%Z TC 8
%Z TC 12
%Z WG 8.4
%Z WG 8.9
%Z WG 12.9
%2 https://inria.hal.science/hal-03414718/document
%2 https://inria.hal.science/hal-03414718/file/497121_1_En_7_Chapter.pdf
%L hal-03414718
%U https://inria.hal.science/hal-03414718
%~ SHS
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-TC8
%~ IFIP-WG8-4
%~ IFIP-WG8-9
%~ IFIP-CD-MAKE
%~ IFIP-WG12-9
%~ IFIP-LNCS-12279