Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP)

TL;DR

This paper introduces LIME-SUP, a novel method for interpreting complex supervised machine learning models locally by using supervised partitioning, which improves interpretability over existing clustering-based approaches.

Contribution

The paper proposes LIME-SUP, a new locally interpretable modeling approach based on supervised partitioning, offering advantages over clustering-based methods like KLIME.

Findings

LIME-SUP effectively interprets complex models in simulations.

LIME-SUP outperforms KLIME in real data applications.

Supervised partitioning provides clearer local explanations.

Abstract

Supervised Machine Learning (SML) algorithms such as Gradient Boosting, Random Forest, and Neural Networks have become popular in recent years due to their increased predictive performance over traditional statistical methods. This is especially true with large data sets (millions or more observations and hundreds to thousands of predictors). However, the complexity of the SML models makes them opaque and hard to interpret without additional tools. There has been a lot of interest recently in developing global and local diagnostics for interpreting and explaining SML models. In this paper, we propose locally interpretable models and effects based on supervised partitioning (trees) referred to as LIME-SUP. This is in contrast with the KLIME approach that is based on clustering the predictor space. We describe LIME-SUP based on fitting trees to the fitted response (LIM-SUP-R) as well as the derivatives of the fitted response (LIME-SUP-D). We compare the results with KLIME and describe its advantages using simulation and real data.