Employee attrition has become one of the major challenges faced by organizations because it affects productivity, increases recruitment cost, and reduces organizational performance. The present study focuses on identifying the major factors responsible for employee attrition and predicting employee turnover using HR Analytics and machine learning techniques. Both primary and secondary data were used for analysis. Primary data were collected from 100 employees through a structured questionnaire, while secondary data were obtained from the IBM HR Analytics Employee Attrition Dataset containing 1,470 employee records. Variables such as age, education, department, salary, overtime, work-life balance, and job satisfaction were analysed.

Statistical tools including percentage analysis and correlation analysis were used for interpretation. Machine learning techniques such as Logistic Regression and Decision Tree were applied to predict employee attrition. The findings revealed that younger employees and employees working in sales departments showed higher attrition tendency. Overtime, low salary, work pressure, and poor work-life balance were identified as major factors influencing employee turnover. Among the prediction models, Logistic Regression produced higher accuracy compared to Decision Tree. The study concludes that organizations should improve employee engagement, career growth opportunities, salary structure, and work-life balance strategies to reduce employee attrition and improve retention.