Predicting employee turnover intention in IT&ITeS industry using machine learning algorithms

Employee' determination to leave the organization is one of the significant factors impacting the performance of the organizations since it affects the overall profitability. Organizations need to strategize to reduce the turnover goals of the workers to have a competitive advantage over other organizations. By understanding the factors impacting the employee's intent to leave the organization, the management can intervene with strategic policies and decisions so that intent of the employees to leave the organization will be reduced substantially and thus increasing the employee's engagement towards work. This research paper uses machine learning algorithms to predict an employee's intention to leave the organization in the near future and identifies the significant features impacting the employee's intention to leave the organization. Data has been collected from 416 employees working in IT and ITES companies using convenience sampling and structure questionnaire. Research also used text mining to analyse the open-ended questionnaire filled by the employees there by mining the frequently used words and employee sentiments. From the study, it is found that among the Classification algorithms used for predicting employee's turnover intention, XG boost performed relatively better with high accuracy, recall, precision and f score. Using Logistic Regression, it is found that alternative job opportunity, gender, education, willing to relocate from the workplace, alternative job opportunity, job stress and attitude towards COVID affects the employee's intent to leave the organization to a greater extent.