Predicting the Employee Turnover Intention: How Organizations Leverage Data-Driven HR Predictive Analytics for Talent Management Decision-Making

Abstract

Turnover intention is an ongoing issue of interest to many organizations. High employee turnover intention can cause numerous negative effects to organizations, including decrease in productivity, increase training expenses and contribute to low employee morale. Thus, this study aimed to predict the employee turnover intention. Using Microsoft Excel and RStudio software, a logistic regression model is used to make predictions and analysed the relationship between variables in this quantitative research, which is based on a secondary dataset that was obtained from Kaggle. The study concluded that age, education field, department, business travel, overtime, total working years, years at company, number of companies worked, job involvement, interpersonal relationship satisfaction, work-life balance, job satisfaction and work environment satisfaction effected the employee turnover intention. However, the Hosmer-Lemeshow goodness-of-fit test indicated that the logistic regression model in this study is poorly fitted due to small sample sizes. For the theoretical contribution, this study provided different perspectives on variables that affect employee turnover intention and minimized the research gap caused by inconsistent results in previous literatures. Meanwhile, for the practical contribution, this study's predictive analytics using logistic regression model aimed to assist organizations to leverage data-driven Human Resource (HR) analytics to strategically manage their talent.