CLE-SH: Comprehensive Literal Explanation package for SHapley values by statistical validity

TL;DR

This paper introduces CLE-SH, a library that enhances the interpretability of SHAP values by providing statistically valid, comprehensive explanations of feature importance and interactions, facilitating better understanding in applied research.

Contribution

The paper presents a novel library that simplifies and statistically validates SHAP analysis, improving its application in various research domains.

Findings

Provides statistically significant feature importance analysis

Offers clear interpretation of feature interactions

Enhances SHAP usability for non-experts

Abstract

Recently, SHapley Additive exPlanations (SHAP) has been widely utilized in various research domains. This is particularly evident in application fields, where SHAP analysis serves as a crucial tool for identifying biomarkers and assisting in result validation. However, despite its frequent usage, SHAP is often not applied in a manner that maximizes its potential contributions. A review of recent papers employing SHAP reveals that many studies subjectively select a limited number of features as 'important' and analyze SHAP values by approximately observing plots without assessing statistical significance. Such superficial application may hinder meaningful contributions to the applied fields. To address this, we propose a library package designed to simplify the interpretation of SHAP values. By simply inputting the original data and SHAP values, our library provides: 1) the number of important features to analyze, 2) the pattern of each feature via univariate analysis, and 3) the interaction between features. All information is extracted based on its statistical significance and presented in simple, comprehensible sentences, enabling users of all levels to understand the interpretations. We hope this library fosters a comprehensive understanding of statistically valid SHAP results.