# Prediction-based Variable Selection for Component-wise Gradient Boosting

## TL;DR

This paper explores prediction-based mechanisms like AIC and cross-validation for variable selection in component-wise gradient boosting, aiming to enhance both selection accuracy and predictive performance.

## Contribution

It introduces and evaluates new prediction-based variable selection methods within component-wise gradient boosting, improving selection quality and prediction accuracy.

## Key findings

- Improved variable selection properties in simulations
- Lowered prediction error in COVID-19 incidence application
- Effective use of AIC and cross-validation in model selection

## Abstract

Model-based component-wise gradient boosting is a popular tool for data-driven variable selection. In order to improve its prediction and selection qualities even further, several modifications of the original algorithm have been developed, that mainly focus on different stopping criteria, leaving the actual variable selection mechanism untouched. We investigate different prediction-based mechanisms for the variable selection step in model-based component-wise gradient boosting. These approaches include Akaikes Information Criterion (AIC) as well as a selection rule relying on the component-wise test error computed via cross-validation. We implemented the AIC and cross-validation routines for Generalized Linear Models and evaluated them regarding their variable selection properties and predictive performance. An extensive simulation study revealed improved selection properties whereas the prediction error could be lowered in a real world application with age-standardized COVID-19 incidence rates.