Predictive Analysis of Employee Turnover: A Comprehensive Model for Attrition Forecasting
Likith Kumar C M
MBA 4th Sem Student
Faculty of Management & Commerce
Ramaiah University of Applied Sciences
Dr. S Ajitha
Associate Professor
Faculty of Management & Commerce
Ramaiah University of Applied Sciences
Ms Reshma K J
Assistant Professor
Faculty of Management & Commerce
Ramaiah University of Applied Sciences
Abstract: Employee attrition has become a critical concern for organizations seeking to maintain a stable workforce and minimize turnover-related costs. This study aims to develop a predictive model to forecast employee attrition by analyzing key factors influencing turnover. The research investigates a range of variables, including push factors (e.g., job dissatisfaction, workplace conflict), pull factors (e.g., external job opportunities), organizational factors (e.g., leadership, culture), and external factors (e.g., economic conditions). The data is collected via a structured questionnaire through Google Forms, which captures responses related to these influencing factors.Using advanced machine learning techniques, this study evaluates multiple models, including logistic regression, decision trees, random forests, and support vector machines, to determine the most accurate model for predicting employee attrition. The evaluation is based on accuracy, precision, recall, and F1-score to ensure a robust prediction. The findings offer organizations valuable insights into the primary causes of employee turnover and provide a data-driven approach to proactively address these issues, reducing attrition rates and improving employee retention strategies. This research contributes to the existing body of knowledge by offering a comprehensive framework for predicting employee attrition, and its practical implications extend to human resource management, organizational development, and strategic planning.
Keywords:
Employee attrition, Turnover prediction, Predictive model, Push factors, Pull factors, Organizational factors, External factors, Machine learning, Logistic regression, Accuracy, Precision, Recall, F1-score, Employee retention, Human resource management, Workforce stability.
