Predicting Employee Attrition Using Behavioral Data

Employee attrition prediction has become a vital area of research within human-resource analytics as organizations seek to retain top talent and reduce recruitment costs. Traditional HR systems depend mainly on static data such as salary, tenure, and department, offering limited insight into dynamic factors that influence employee decisions to leave. Recent advances in Machine Learning (ML) and behavioural analytics have enabled proactive identification of at-risk employees by examining digital behaviour patterns, engagement trends, and workplace activity. This paper surveys current approaches for predicting employee attrition, emphasizing behavioural feature extraction, classification models, evaluation metrics, and visualization dashboards.