Title: Improved XGBoost model based on genetic algorithm
Authors: Jinxiang Chen; Feng Zhao; Yanguang Sun; Yilan Yin
Addresses: State Key Laboratory of Hybrid Process Industry Automation Systems and Equipment Technology, Automation Research and Design Institute of Metallurgical Industry, China Iron & Steel Research Institute Group, Beijing 100081, China ' State Key Laboratory of Hybrid Process Industry Automation Systems and Equipment Technology, Automation Research and Design Institute of Metallurgical Industry, China Iron & Steel Research Institute Group, Beijing 100081, China ' State Key Laboratory of Hybrid Process Industry Automation Systems and Equipment Technology, Automation Research and Design Institute of Metallurgical Industry, China Iron & Steel Research Institute Group, Beijing 100081, China ' State Key Laboratory of Hybrid Process Industry Automation Systems and Equipment Technology, Automation Research and Design Institute of Metallurgical Industry, China Iron & Steel Research Institute Group, Beijing 100081, China
Abstract: An optimised XGBoost model based on genetic algorithm to search for optimal parameter combinations is proposed in this paper. It was proved that the improved algorithm has better classification effect than existing approaches through the liver disease data set Liver Disorders Data Set in the UCI Machine Learning Repository. In recent years, there have been many excellent intelligent algorithms in the field of machine learning and XGBoost is one of them. However, when using the XGBoost algorithm, it usually involves the adjustment of various parameters in the XGBoost model, and the classification performance of the model will be greatly influenced by the selection of parameters and their combination methods. In this paper, after encoding the XGBoost model parameters optimised by genetic algorithm, the global approximate optimal solution is obtained through operations such as selection, crossover and mutation, which greatly improves the performance of the model.
Keywords: XGBoost; parameter optimisation; genetic algorithm.
DOI: 10.1504/IJCAT.2020.106571
International Journal of Computer Applications in Technology, 2020 Vol.62 No.3, pp.240 - 245
Received: 17 May 2019
Accepted: 17 Jun 2019
Published online: 15 Apr 2020 *