Automatic Componentwise Boosting: An Interpretable AutoML System

TL;DR

This paper introduces autocompboost, an AutoML system that constructs interpretable additive models using componentwise boosting, balancing predictive performance with transparency and ease of interpretation for practitioners.

Contribution

It presents a novel AutoML framework that builds interpretable models with scalable boosting, contrasting with black-box ensemble methods.

Findings

Competitive predictive performance on benchmark datasets

Enhanced interpretability through visualization tools

Efficient model fitting with scalable boosting algorithms

Abstract

In practice, machine learning (ML) workflows require various different steps, from data preprocessing, missing value imputation, model selection, to model tuning as well as model evaluation. Many of these steps rely on human ML experts. AutoML - the field of automating these ML pipelines - tries to help practitioners to apply ML off-the-shelf without any expert knowledge. Most modern AutoML systems like auto-sklearn, H20-AutoML or TPOT aim for high predictive performance, thereby generating ensembles that consist almost exclusively of black-box models. This, in turn, makes the interpretation for the layperson more intricate and adds another layer of opacity for users. We propose an AutoML system that constructs an interpretable additive model that can be fitted using a highly scalable componentwise boosting algorithm. Our system provides tools for easy model interpretation such as visualizing partial effects and pairwise interactions, allows for a straightforward calculation of feature importance, and gives insights into the required model complexity to fit the given task. We introduce the general framework and outline its implementation autocompboost. To demonstrate the frameworks efficacy, we compare autocompboost to other existing systems based on the OpenML AutoML-Benchmark. Despite its restriction to an interpretable model space, our system is competitive in terms of predictive performance on most data sets while being more user-friendly and transparent.