Local Multi-Label Explanations for Random Forest

TL;DR

This paper introduces a method for explaining multi-label predictions of random forests, adapting a single-label explanation technique to improve interpretability in complex, real-world multi-label classification tasks.

Contribution

It extends the LionForests explanation technique to multi-label classification, employing three strategies to enhance interpretability of random forest models.

Findings

Effective explanations for multi-label random forest predictions.

Improved interpretability in high-stakes domains like healthcare and finance.

Quantitative and qualitative validation of the proposed method.

Abstract

Multi-label classification is a challenging task, particularly in domains where the number of labels to be predicted is large. Deep neural networks are often effective at multi-label classification of images and textual data. When dealing with tabular data, however, conventional machine learning algorithms, such as tree ensembles, appear to outperform competition. Random forest, being a popular ensemble algorithm, has found use in a wide range of real-world problems. Such problems include fraud detection in the financial domain, crime hotspot detection in the legal sector, and in the biomedical field, disease probability prediction when patient records are accessible. Since they have an impact on people's lives, these domains usually require decision-making systems to be explainable. Random Forest falls short on this property, especially when a large number of tree predictors are used. This issue was addressed in a recent research named LionForests, regarding single label classification and regression. In this work, we adapt this technique to multi-label classification problems, by employing three different strategies regarding the labels that the explanation covers. Finally, we provide a set of qualitative and quantitative experiments to assess the efficacy of this approach.