Enhancing sampling performance in XGBoost by ensemble feature engineering

Lingping Kong

doi:10.1016/j.patcog.2026.113169

Enhancing sampling performance in XGBoost by ensemble feature engineering

2026-01-28

0

PRE

AI

L

Lingping Kong

P

Ponnuthurai Nagaratnam Suganthan

DOI：10.1016/j.patcog.2026.113169

Original

Original request for help

Save

Abstract

En 中文

• We propose the Feat-XGBoost classifier for improved generalization on complex datasets. • We propose the Mix-XGBoost method to enhance performance at the decision stage. • We validate our approach using 61 standard ML datasets from the UCI repository. • This study highlights targeted feature engineering at each boosting step.

Keywords:

Feat-XGBoost

Mix-XGBoost

feature engineering

XGBoost

ensemble learning

Enhancing sampling performance in XGBoost by ensemble feature engineering

Abstract

Journal

Organization