Rationale: The ability to predict voluntary turnover is crucial for every company to prevent a broad range of financial losses. This prediction is usually based on time- consuming surveys with low response rates.
Purpose: The research question of this paper is whether the available data in the Human Resources system can result in reliable turnover predictions without supplementary survey information.
Methodology: In the present paper a logistic regression model is introduced for analyzing turnover. The methodology is illustrated on a real life dataset of a Belgian branch of a private company. The model performance is evaluated by the AUC measure.
Findings: It can be concluded that data in the personnel system indeed leads to valuable predictions of turnover.
Practical implications: The presented approach brings determinants of voluntary turnover to the surface. The results yield useful information for Human Resources departments. The logistic regression results in a turnover probability at the individual level. With the dataset based approach, each company can, immediately, ascertain their own turnover risk.
Originality: The study of a data driven approach for turnover investigation has not been done
Original languageEnglish
Pages (from-to)96-112
Number of pages17
JournalManagement Research Review
Issue number1
Publication statusPublished - Jan 2018

    Research areas

  • Database analysis, Human resource management, Human resources analytics, Logistic regression, Manpower planning, Turnover, Wastage

ID: 35535920