Interpretable Quantile Regression by Optimal Decision Trees

TL;DR

This paper introduces a novel method for learning optimal quantile regression trees that are interpretable, distribution-agnostic, and computationally efficient, enhancing trust and understanding in AI models.

Contribution

It proposes a new approach to quantile regression trees that balances interpretability, accuracy, and efficiency without assuming specific distributional forms.

Findings

Provides complete conditional distribution predictions without distributional assumptions.

Learns a set of optimal quantile regression trees efficiently.

Enhances interpretability and trust in machine learning models.

Abstract

The field of machine learning is subject to an increasing interest in models that are not only accurate but also interpretable and robust, thus allowing their end users to understand and trust AI systems. This paper presents a novel method for learning a set of optimal quantile regression trees. The advantages of this method are that (1) it provides predictions about the complete conditional distribution of a target variable without prior assumptions on this distribution; (2) it provides predictions that are interpretable; (3) it learns a set of optimal quantile regression trees without compromising algorithmic efficiency compared to learning a single tree.