Predicting Employee Attrition Using Machine Learning: A Systematic Literature Review

Abstract

Employee attrition, or the voluntary turnover of employees, is a major concern for businesses worldwide due to the increased competition and dynamic changes in the business environment. Predicting employee attrition can help organizations improve their retention strategies and enhance their performance. This article presents a Systematic Literature Review (SLR) of the previous studies that have applied machine learning techniques to predict employee attrition. The SLR covers the data sources, the machine learning models, and the evaluation metrics used in the existing literature. The article reveals the challenges of obtaining reliable and relevant data for attrition prediction and suggests some possible solutions. The article also compares the performance of different machine learning models, such as support vector machines (SVMs), decision trees, random forests, and neural networks, using various evaluation metrics, such as accuracy, precision, recall, and F1-score. The article shows that using multiple machine learning models and evaluation metrics can provide more reliable and robust results than relying on a single model or metric. The article concludes by highlighting the contributions and limitations of the current research and proposing some directions for future research. This article is a valuable resource for researchers and practitioners in the fields of business analytics and human resources, as it provides a comprehensive overview and analysis of the state-of-the-art in employee attrition prediction using machine learning techniques.