Rigorous Explanations for Tree Ensembles

TL;DR

This paper explores methods to generate rigorous, logically-sound explanations for predictions made by tree ensembles like random forests and boosted trees, enhancing interpretability and trust.

Contribution

It introduces a framework for computing explanations that are rigorously defined and truly reflect the properties of tree ensemble models.

Findings

Developed methods for rigorous explanations of tree ensembles

Demonstrated explanations accurately reflect model behavior

Enhanced trustworthiness of model interpretability

Abstract

Tree ensembles (TEs) find a multitude of practical applications. They represent one of the most general and accurate classes of machine learning methods. While they are typically quite concise in representation, their operation remains inscrutable to human decision makers. One solution to build trust in the operation of TEs is to automatically identify explanations for the predictions made. Evidently, we can only achieve trust using explanations, if those explanations are rigorous, that is truly reflect properties of the underlying predictor they explain This paper investigates the computation of rigorously-defined, logically-sound explanations for the concrete case of two well-known examples of tree ensembles, namely random forests and boosted trees.