Abstract
Data mining methods have been used to study a variety of topics in industrial and organizational psychology, including predicting employee performance. With the increased interest in predictive analytics in human resources, the present study aimed to review and explore the application of two commonly used data mining methods, decision trees (DTs) and artificial neural networks (ANNs), for predicting employee performance in organizational settings. Out of 103 studies reviewed, eight studies were retained and used for the meta-analyses. The number of employee performance classifications meta-analyzed was 2430 in total. The results suggested that both data mining methods showed good performance in employee performance prediction, although the difference between the overall effect sizes was not statistically significant. The theoretical and practical implications and the potential limitations were discussed, and recommendations were provided for future research directions. The current study was a first attempt to qualitatively and quantitatively evaluate the effectiveness of the data mining methods in predicting employee performance.
Notes
If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu
Graduation Date
2021
Semester
Spring
Advisor
Su, Shiyang
Degree
Master of Science (M.S.)
College
College of Sciences
Department
Psychology
Degree Program
Industrial and Organizational Psychology
Format
application/pdf
Identifier
CFE0008471; DP0024147
URL
https://purls.library.ucf.edu/go/DP0024147
Language
English
Release Date
May 2022
Length of Campus-only Access
1 year
Access Status
Masters Thesis (Open Access)
STARS Citation
Erengin, Turku, "Predicting Employee Performance: A Meta-Analysis and Systematic Review on Data Mining Methods" (2021). Electronic Theses and Dissertations, 2020-2023. 500.
https://stars.library.ucf.edu/etd2020/500