Conclusive Local Interpretation Rules for Random Forests

TL;DR

This paper introduces LionForests, a novel interpretation method for random forests that provides conclusive, rule-based explanations applicable across various tasks, supported by theoretical guarantees and validated through experiments.

Contribution

LionForests is a new random forest interpretation technique offering conclusive, rule-based explanations with a solid theoretical foundation and broad applicability.

Findings

LionForests provides valid, conclusive rules for model explanations.

It outperforms state-of-the-art interpretability methods in experiments.

The method is applicable to classification and regression tasks.

Abstract

In critical situations involving discrimination, gender inequality, economic damage, and even the possibility of casualties, machine learning models must be able to provide clear interpretations for their decisions. Otherwise, their obscure decision-making processes can lead to socioethical issues as they interfere with people's lives. In the aforementioned sectors, random forest algorithms strive, thus their ability to explain themselves is an obvious requirement. In this paper, we present LionForests, which relies on a preliminary work of ours. LionForests is a random forest-specific interpretation technique, which provides rules as explanations. It is applicable from binary classification tasks to multi-class classification and regression tasks, and it is supported by a stable theoretical background. Experimentation, including sensitivity analysis and comparison with state-of-the-art techniques, is also performed to demonstrate the efficacy of our contribution. Finally, we highlight a unique property of LionForests, called conclusiveness, that provides interpretation validity and distinguishes it from previous techniques.