EMPLOYEE ATTRITION PREDICTION USING MACHINE LEARNING MODELS

Abstract

Employee attrition is a critical challenge faced by organizations, directly impacting productivity, morale, and operational costs. This research aims to predict employee attrition using various machine learning algorithms including Logistic Regression, Decision Tree, Random Forest, Support Vector Classifier (SVC), K-Nearest Neighbors (KNN), Gaussian Naïve Bayes, Gradient Boosting, and XGBoost. The HR dataset was preprocessed, encoded, and analyzed to extract key features contributing to employee turnover. Multiple models were trained and evaluated based on accuracy, precision, recall, and F1-score metrics. Preliminary results indicate that ensemble methods such as Random Forest and XGBoost outperform traditional models in predicting attrition. This study provides insights into employee retention strategies through predictive modeling and data-driven analysis.