Embedded Constrained Feature Construction for High-Energy Physics Data Classification

TL;DR

This paper introduces a framework for embedding constrained feature construction into tree-based models to improve classification performance in high-energy physics data analysis, ensuring interpretability and transparency.

Contribution

It presents a novel method to incorporate feature construction directly into model induction, tailored for high-energy physics constraints, enhancing interpretability and performance.

Findings

Significant improvement in classification scores

Reduced number of constructed features

Models remain transparent and interpretable

Abstract

Before any publication, data analysis of high-energy physics experiments must be validated. This validation is granted only if a perfect understanding of the data and the analysis process is demonstrated. Therefore, physicists prefer using transparent machine learning algorithms whose performances highly rely on the suitability of the provided input features. To transform the feature space, feature construction aims at automatically generating new relevant features. Whereas most of previous works in this area perform the feature construction prior to the model training, we propose here a general framework to embed a feature construction technique adapted to the constraints of high-energy physics in the induction of tree-based models. Experiments on two high-energy physics datasets confirm that a significant gain is obtained on the classification scores, while limiting the number of built features. Since the features are built to be interpretable, the whole model is transparent and readable.