Contextual Decision Trees

TL;DR

This paper introduces a dynamic, context-aware decision tree selection method based on Random Forests, enabling local interpretability and maintaining competitive predictive performance.

Contribution

It presents a novel framework for selecting a single, shallow tree from a Random Forest dynamically based on context, enhancing interpretability without sacrificing accuracy.

Findings

Outperforms independent CART decision trees in predictive accuracy.

Comparable to full Random Forests in performance.

Provides local interpretability through rule observation.

Abstract

Focusing on Random Forests, we propose a multi-armed contextual bandit recommendation framework for feature-based selection of a single shallow tree of the learned ensemble. The trained system, which works on top of the Random Forest, dynamically identifies a base predictor that is responsible for providing the final output. In this way, we obtain local interpretations by observing the rules of the recommended tree. The carried out experiments reveal that our dynamic method is superior to an independent fitted CART decision tree and comparable to the whole black-box Random Forest in terms of predictive performances.