Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithms

TL;DR

This paper introduces a locally-interpretable surrogate model for complex supervised machine learning algorithms, using model-based trees and simple models at each node to enhance interpretability without sacrificing much predictive accuracy.

Contribution

It proposes a novel surrogate modeling approach that partitions the predictor space with regression trees and fits simple models locally, improving interpretability of complex ML models.

Findings

The surrogate model provides good interpretability of complex ML algorithms.

It maintains reasonably high predictive performance.

The method is efficient for high-dimensional data.

Abstract

Supervised Machine Learning (SML) algorithms, such as Gradient Boosting, Random Forest, and Neural Networks, have become popular in recent years due to their superior predictive performance over traditional statistical methods. However, their complexity makes the results hard to interpret without additional tools. There has been a lot of recent work in developing global and local diagnostics for interpreting SML models. In this paper, we propose a locally-interpretable model that takes the fitted ML response surface, partitions the predictor space using model-based regression trees, and fits interpretable main-effects models at each of the nodes. We adapt the algorithm to be efficient in dealing with high-dimensional predictors. While the main focus is on interpretability, the resulting surrogate model also has reasonably good predictive performance.