Globally Interpretable Classifiers via Boolean Formulas with Dynamic Propositions

TL;DR

This paper introduces a method for creating human-interpretable classifiers using Boolean formulas with dynamic propositions, ensuring transparency while maintaining accuracy comparable to state-of-the-art models.

Contribution

The paper presents a novel approach to extract simple, interpretable Boolean classifiers from tabular data using Answer Set Programming, enhancing transparency in AI models.

Findings

Classifiers are as accurate as XGBoost and random forests.

Results show classifiers are short and human-readable.

Method is effective across multiple datasets.

Abstract

Interpretability and explainability are among the most important challenges of modern artificial intelligence, being mentioned even in various legislative sources. In this article, we develop a method for extracting immediately human interpretable classifiers from tabular data. The classifiers are given in the form of short Boolean formulas built with propositions that can either be directly extracted from categorical attributes or dynamically computed from numeric ones. Our method is implemented using Answer Set Programming. We investigate seven datasets and compare our results to ones obtainable by state-of-the-art classifiers for tabular data, namely, XGBoost and random forests. Over all datasets, the accuracies obtainable by our method are similar to the reference methods. The advantage of our classifiers in all cases is that they are very short and immediately human intelligible as opposed to the black-box nature of the reference methods.