Explanations Based on Item Response Theory (eXirt): A Model-Specific Method to Explain Tree-Ensemble Model in Trust Perspective

TL;DR

This paper introduces eXirt, a novel XAI method based on Item Response Theory, to generate global and local explanations for tree-ensemble models in binary classification, enhancing model interpretability and trust.

Contribution

The paper proposes eXirt, a new IRT-based method for explaining tree-ensemble models, providing both global feature relevance rankings and local instance explanations.

Findings

eXirt produces explanations comparable to existing XAI methods.

eXirt offers both global and local interpretability for tree-ensemble models.

The method enhances understanding and trust in black box models.

Abstract

In recent years, XAI researchers have been formalizing proposals and developing new methods to explain black box models, with no general consensus in the community on which method to use to explain these models, with this choice being almost directly linked to the popularity of a specific method. Methods such as Ciu, Dalex, Eli5, Lofo, Shap and Skater emerged with the proposal to explain black box models through global rankings of feature relevance, which based on different methodologies, generate global explanations that indicate how the model's inputs explain its predictions. In this context, 41 datasets, 4 tree-ensemble algorithms (Light Gradient Boosting, CatBoost, Random Forest, and Gradient Boosting), and 6 XAI methods were used to support the launch of a new XAI method, called eXirt, based on Item Response Theory - IRT and aimed at tree-ensemble black box models that use tabular data referring to binary classification problems. In the first set of analyses, the 164 global feature relevance ranks of the eXirt were compared with 984 ranks of the other XAI methods present in the literature, seeking to highlight their similarities and differences. In a second analysis, exclusive explanations of the eXirt based on Explanation-by-example were presented that help in understanding the model trust. Thus, it was verified that eXirt is able to generate global explanations of tree-ensemble models and also local explanations of instances of models through IRT, showing how this consolidated theory can be used in machine learning in order to obtain explainable and reliable models.