Explainability of Machine Learning Models under Missing Data

TL;DR

This paper investigates how different data imputation methods affect the explainability of machine learning models, especially using SHAP values, highlighting biases introduced by imputation choices and their impact on model interpretation.

Contribution

It provides a comprehensive analysis of imputation strategies on SHAP explanations, including theoretical insights and practical guidelines for improving model interpretability with missing data.

Findings

Imputation methods can bias Shapley values and affect explainability.

Lower prediction MSE does not guarantee lower MSE in Shapley values.

Using XGBoost directly on missing data can impair interpretability.

Abstract

Missing data is a prevalent issue that can significantly impair model performance and explainability. This paper briefly summarizes the development of the field of missing data with respect to Explainable Artificial Intelligence and experimentally investigates the effects of various imputation methods on SHAP (SHapley Additive exPlanations), a popular technique for explaining the output of complex machine learning models. Next, we compare different imputation strategies and assess their impact on feature importance and interaction as determined by Shapley values. Moreover, we also theoretically analyze the effects of missing values on Shapley values. Importantly, our findings reveal that the choice of imputation method can introduce biases that could lead to changes in the Shapley values, thereby affecting the explainability of the model. Moreover, we also show that a lower test prediction MSE (Mean Square Error) does not necessarily imply a lower MSE in Shapley values and vice versa. Also, while XGBoost (eXtreme Gradient Boosting) is a method that could handle missing data directly, using XGBoost directly on missing data can seriously affect explainability compared to imputing the data before training XGBoost. This study provides a comprehensive evaluation of imputation methods in the context of model explanations, offering practical guidance for selecting appropriate techniques based on dataset characteristics and analysis objectives. The results underscore the importance of considering imputation effects to ensure robust and reliable insights from machine learning models.