Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction

TL;DR

This study evaluates whether explanations from various XAI methods align with human experts' expectations in a homicide prediction model, finding that 75% of human interpretability expectations are met and about 48% agreement exists between XAI outputs and human judgments.

Contribution

It provides an empirical analysis of the alignment between XAI-generated explanations and human interpretability expectations in a real-world homicide prediction task.

Findings

75% of human expectations were met by XAI explanations

Approximately 48% agreement between XAI methods and human experts

Different XAI methods produce similar explanations for the problem

Abstract

Strategies based on Explainable Artificial Intelligence (XAI) have promoted better human interpretability of the results of black box models. This opens up the possibility of questioning whether explanations created by XAI methods meet human expectations. The XAI methods being currently used (Ciu, Dalex, Eli5, Lofo, Shap, and Skater) provide various forms of explanations, including global rankings of relevance of features, which allow for an overview of how the model is explained as a result of its inputs and outputs. These methods provide for an increase in the explainability of the model and a greater interpretability grounded on the context of the problem. Intending to shed light on the explanations generated by XAI methods and their interpretations, this research addresses a real-world classification problem related to homicide prediction, already peer-validated, replicated its proposed black box model and used 6 different XAI methods to generate explanations and 6 different human experts. The results were generated through calculations of correlations, comparative analysis and identification of relationships between all ranks of features produced. It was found that even though it is a model that is difficult to explain, 75\% of the expectations of human experts were met, with approximately 48\% agreement between results from XAI methods and human experts. The results allow for answering questions such as: "Are the Expectation of Interpretation generated among different human experts similar?", "Do the different XAI methods generate similar explanations for the proposed problem?", "Can explanations generated by XAI methods meet human expectation of Interpretations?", and "Can Explanations and Expectations of Interpretation work together?".