id
	15453
Url
	https://chloe.cnr.it/s/BiDiAr/item/15453
Resource template
	Conference Paper
Resource class
	fabio:ConferencePaper
Title
	A Unified Approach to Interpreting Model Predictions
Creator
	Lundberg, Scott
	Lee, Su-In
Date
	2017
Language
	eng
Abstract
	Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension between accuracy and interpretability. In response, various methods have recently been proposed to help users interpret the predictions of complex models, but it is often unclear how these methods are related and when one method is preferable over another. To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature an importance value for a particular prediction. Its novel components include: (1) the identification of a new class of additive feature importance measures, and (2) theoretical results showing there is a unique solution in this class with a set of desirable properties. The new class unifies six existing methods, notable because several recent methods in the class lack the proposed desirable properties. Based on insights from this unification, we present new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.
Is Part Of
	in Proceedings 31st Conference on Neural Information Processing Systems (NIPS) (Long Beach 2017)
Doi
	https://doi.org/10.48550/arXiv.1705.07874
Pages
	1-ott
Uri
	http://arxiv.org/abs/1705.07874
Homepage
	https://www.zotero.org/groups/5293298/bidiar/items/YLPMNFQU/item-list

--