Globally Interpretable Classifiers via Boolean Formulas with Dynamic Propositions
This addresses the need for human-interpretable AI models in domains requiring transparency, though it is incremental as it builds on existing interpretability techniques.
The authors tackled the problem of creating interpretable classifiers from tabular data by developing a method that generates short Boolean formulas, achieving accuracies similar to state-of-the-art methods like XGBoost and random forests across seven datasets.
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.