A Unified Approach to Interpreting Model Predictions

by   Scott Lundberg, et al.
University of Washington

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.


page 1

page 2

page 3

page 4


An unexpected unity among methods for interpreting model predictions

Understanding why a model made a certain prediction is crucial in many d...

Understanding Global Feature Contributions Through Additive Importance Measures

Understanding the inner workings of complex machine learning models is a...

Explaining by Removing: A Unified Framework for Model Explanation

Researchers have proposed a wide variety of model explanation approaches...

TSInterpret: A unified framework for time series interpretability

With the increasing application of deep learning algorithms to time seri...

Generalized Sparse Additive Models

We present a unified framework for estimation and analysis of generalize...

The Berkelmans-Pries Feature Importance Method: A Generic Measure of Informativeness of Features

Over the past few years, the use of machine learning models has emerged ...

Please sign up or login with your details

Forgot password? Click here to reset