Case-based Explainability for Random Forest: Prototypes, Critics, Counter-factuals and Semi-factuals

TL;DR

This paper explores explainable case-based reasoning for Random Forests by identifying prototypes, critics, and counter-factuals, enhancing transparency in black-box models for regulated industries.

Contribution

It introduces a novel approach to extract and utilize data-driven explanations like prototypes and counter-factuals specifically for Random Forest models.

Findings

Effective identification of prototypes and critics improves explanation quality.

Counter-factuals and semi-factuals provide actionable insights.

Evaluation metrics confirm the explanatory power of the proposed methods.

Abstract

The explainability of black-box machine learning algorithms, commonly known as Explainable Artificial Intelligence (XAI), has become crucial for financial and other regulated industrial applications due to regulatory requirements and the need for transparency in business practices. Among the various paradigms of XAI, Explainable Case-Based Reasoning (XCBR) stands out as a pragmatic approach that elucidates the output of a model by referencing actual examples from the data used to train or test the model. Despite its potential, XCBR has been relatively underexplored for many algorithms such as tree-based models until recently. We start by observing that most XCBR methods are defined based on the distance metric learned by the algorithm. By utilizing a recently proposed technique to extract the distance metric learned by Random Forests (RFs), which is both geometry- and accuracy-preserving, we investigate various XCBR methods. These methods amount to identify special points from the training datasets, such as prototypes, critics, counter-factuals, and semi-factuals, to explain the predictions for a given query of the RF. We evaluate these special points using various evaluation metrics to assess their explanatory power and effectiveness.