Research on Accurate Identification of Poor Students - A Case Study of Jiangsu Province  
Author Junjie Zhu


Co-Author(s) Butong Li; Weihao Liu; Xufeng Zhao


Abstract Identifying poor students is a significant problem for all walks of life, especially in education. With the development of machine learning algorithms, researchers have been finding progressively sophisticated ways to recognize poor students, but practical implementations are rarely reported. The paper explores the combination of the PSO algorithm and the LightGBM algorithm, gives insights into the complete development process, and compares different machine learning methods. The experimental results reveal that our proposed poverty prediction index model based on PSO-LightGBM has an excellent performance in training resource consumption, model evaluation, and prediction accuracy.


Keywords Machine learning, PSO, LightGBM, Identification of poor students
    Article #:  DSBFI23-116
Proceedings of 2nd ISSAT International Conference on Data Science in Business, Finance and Industry
January 8-10, 2023 - Da Nang, Vietnam