Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26–28, 2023, Nanjing, China

Research Article

Salary Prediction Based on the Dual-Adaboosting System

Download235 downloads
  • @INPROCEEDINGS{10.4108/eai.26-5-2023.2334428,
        author={Yanming Chen and Kunye Zhan and Songguang Lin and Ken Yao},
        title={Salary Prediction Based on the Dual-Adaboosting System},
        proceedings={Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26--28, 2023, Nanjing, China},
        publisher={EAI},
        proceedings_a={MSEA},
        year={2023},
        month={7},
        keywords={salary prediction; adaboosting regression; dual-adaboosting system; machine learning; ensemble learning; randomforest; feature filtering},
        doi={10.4108/eai.26-5-2023.2334428}
    }
    
  • Yanming Chen
    Kunye Zhan
    Songguang Lin
    Ken Yao
    Year: 2023
    Salary Prediction Based on the Dual-Adaboosting System
    MSEA
    EAI
    DOI: 10.4108/eai.26-5-2023.2334428
Yanming Chen1,*, Kunye Zhan2, Songguang Lin3, Ken Yao2
  • 1: Student, Shantou University
  • 2: Student, Shenzhen University
  • 3: Student, Sun Yat-sen University
*Contact email: 21ymchen@stu.edu.cn

Abstract

This paper aims to build a salary prediction model based on the Dual-Adaboosting System which is an improvement method of the Adaboosting algorithm. Adaboosting feature importance ranking method is employed for the paper to conduct feature filtering after the dataset is cleaned and preprocessed. Afterward, regression prediction models were established using different methods to help obtain comparative and analytical results based on RMSE and MAE, serving as a control experiment. Finally, we conducted experiments using the Dual-Adaboosting system and obtained the final salary prediction model. This model definitely has practical reference significance for human resources management and the improvement of the Adaboosting algorithm.