.png){kind=icon}
.png){kind=icon}
Return
Machine Learning Techniques in Predicting Employee Turnover Intention
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-08570-2_19.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study investigates the application of machine learning techniques in predicting employee turnover intention, a critical challenge in human resource management. Specifically, the research compares the performance of three machine learning algorithms-Decision Trees, Neural Networks, and Support Vector Machines (SVM)-on a dataset of 511 employees from different organizations in Croatia. The analysis shows that the Decision Tree model, particularly the RandomTree algorithm, achieved a recall rate of 59%, while the Neural Network model (Multilayer Perceptron) outperformed with a recall rate of 63%, indicating its superior ability to recognize employees who are likely to leave. The SVM model, on the other hand, was less effective with a recall rate of 48%. Job satisfaction, organizational commitment, and perceived alternative job opportunities were identified as significant predictors, highlighting their influence on turnover intention. The findings underscore the potential of machine learning, especially Neural Networks, in enhancing employee retention strategies by proactively identifying at-risk employees.
Keywords:
Employee turnover
Employee job satisfaction
Decision trees
Neural networks
Support vector machines
Journal
E
IF:
0
Papers:
21
Citations:
0