A Novel Approach To Unveiling Employee Attrition Patterns using Machine Learning Algorithms

Abstract

The negative effects of employee turnover upon productivity at work as well as long-term growth initiatives make it a top issue for businesses. To combat this issue, businesses are increasingly relying on machine learning tools for accurate turnover forecasting and management. In this study, we set out to create a model that can accurately forecast future rates of employee turnover. In this research, we use HR analytics data from the Kaggle platform to predict outcomes using a variety of different machine learning techniques, including the Random Forest, Logistic Regressor, Gradient Boosting Classifier, CatBoost Classifier, Extreme Gradient Boosting, and Light GBM. This research goes beyond simple forecasting to investigate the many elements outside of the workplace that contribute to employee turnover. Moreover, our findings aim to provide top management with an insightful perspective, empowering informed decisions concerning strategies for workforce retention. Looking ahead, future research could refine the analysis by encompassing additional factors. Factors such as feedback, recognition, hiring procedures, and organizational culture, which have been observed to positively influence employee attrition rates, hold promise in offering a more comprehensive understanding and effective mitigation strategies.