Employee Performance Prediction based on the Second-order Stacking Algorithm

Yanming Chen; Xinyu Lin; Kunye Zhan

Proceedings of the 2nd International Conference on Financial Innovation, FinTech and Information Technology, FFIT 2023, July 7–9, 2023, Chongqing, China

Research Article

Employee Performance Prediction based on the Second-order Stacking Algorithm

Download125 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/eai.7-7-2023.2338055,
    author={Yanming  Chen and Xinyu  Lin and Kunye  Zhan},
    title={Employee Performance Prediction based on the Second-order Stacking Algorithm},
    proceedings={Proceedings of the 2nd International Conference on Financial Innovation, FinTech and Information Technology, FFIT 2023, July 7--9, 2023, Chongqing, China},
    publisher={EAI},
    proceedings_a={FFIT},
    year={2023},
    month={10},
    keywords={employee performance second-order stacking algorithm machine learning ensemble learning adaboosting},
    doi={10.4108/eai.7-7-2023.2338055}
}

Yanming Chen
Xinyu Lin
Kunye Zhan
Year: 2023
Employee Performance Prediction based on the Second-order Stacking Algorithm
FFIT
EAI
DOI: 10.4108/eai.7-7-2023.2338055

Yanming Chen¹^,*, Xinyu Lin², Kunye Zhan³

1: Shantou University
2: South China Normal University
3: Shenzhen University

*Contact email: 21ymchen@stu.edu.cn

Abstract

This paper attempts to establish an performance prediction model for employees in the field of human resource management based on the second-order stacking algorithm which is an improvement of stacking algorithm. Firstly, the Adaboosting feature importance ranking method is used for feature selection, and then bagging and stacking algorithms are used to establish regression models as control experiments. Finally, a second-order stacking algorithm is used to establish a performance prediction model for employees, achieving minimal error.

Keywords: employee performance second-order stacking algorithm machine learning ensemble learning adaboosting

Published: 2023-10-26
Publisher: EAI

: http://dx.doi.org/10.4108/eai.7-7-2023.2338055