##plugins.themes.bootstrap3.article.main##

Dr.Sinduja.R

Dr. J. Vijayalakshmi

Dr. K.K.Thavamani

Abstract

Employee attrition significantly impacts organizational productivity and costs. This study uses HR analytics and machine learning to analyze attrition data, aiming to understand attrition drivers, develop predictive models, and provide HR insights. The dataset from XYZ corporation included various demographic and employment variables. Data pre- processing involved handling missing values, normalizing data, and using feature selection techniques to identify key attrition factors. Decision Tree and Random Forest classifiers achieved predictive accuracies of 98.87% and 99.66%, respectively, and were validated through cross-validation. Key attrition predictors identified were job satisfaction, tenure, performance ratings, and work-life balance. The application of machine learning revealed complex data relationships not evident through traditional methods. Findings highlight the importance of HR analytics in transforming data into actionable insights, allowing HR departments to proactively address attrition causes and develop targeted retention strategies. The study demonstrates the potential of HR analytics and machine learning in predicting attrition and formulating effective HR strategies, offering a replicable model for organizations to manage talent and minimize turnover impacts.

##plugins.themes.bootstrap3.article.details##