Evaluation of Machine Learning Based Selected Predictive Models for Voluntary Employee Turnover

Abstract

Employee attrition has become one of the most significant problems for any organization. Employees are important assets   of the organization and the subjects who own other valuable resources that the organization need, diverse opportunity costs occur when employee attrition takes place. To prevent such unwanted loss of valuable assets, various efforts have been made to predict and prevent employee attrition. Various methods have been developed, in order to predict employee turnover, including statistical models and machine learning techniques. Statistical models, such as logistic regression and survival analysis, have been used to identify the relationships between different predictor variables and employee turnover. Machine learning algorithms, have also been applied to extract sensitive parameters and better turnover prediction by removing parameters that are not important and instead add to noise.