An Interpretable Rule Creation Method for Black-Box Models based on Surrogate Trees -- SRules

TL;DR

The paper tackles the challenge of interpreting black-box models by introducing SRules, a post-hoc method that derives concise, high-precision production rules from ensembles through surrogate binary trees and a conditional information-gain framework. By ranking features via Gini-impurity-based importance and selecting statistically significant patterns with a chi-square-like test, SRules yields interpretable rule sets $R^*$ that approximate the original model’s decisions. The authors demonstrate that non-recursive SRules often reduces the rule burden while maintaining performance, and that Recursive SRules can improve coverage at the cost of more rules, with overall improvements supported by statistical tests across multiple datasets. This approach offers a practical balance between accuracy, interpretability, and coverage, with potential applications in domains requiring transparent AI, such as medicine and law, while noting limitations like the binary-input focus and opportunities to extend to continuous features and model-agnostic explanations.

Abstract

As artificial intelligence (AI) systems become increasingly integrated into critical decision-making processes, the need for transparent and interpretable models has become paramount. In this article we present a new ruleset creation method based on surrogate decision trees (SRules), designed to improve the interpretability of black-box machine learning models. SRules balances the accuracy, coverage, and interpretability of machine learning models by recursively creating surrogate interpretable decision tree models that approximate the decision boundaries of a complex model. We propose a systematic framework for generating concise and meaningful rules from these surrogate models, allowing stakeholders to understand and trust the AI system's decision-making process. Our approach not only provides interpretable rules, but also quantifies the confidence and coverage of these rules. The proposed model allows to adjust its parameters to counteract the lack of interpretability by precision and coverage by allowing a near perfect fit and high interpretability of some parts of the model . The results show that SRules improves on other state-of-the-art techniques and introduces the possibility of creating highly interpretable specific rules for specific sub-parts of the model.