Cognizant Prognostication: An In-Depth Comparative Study of Machine Learning Models for Predictive Employee Turnover Analysis in the Realm of Human Resources Analytics

This research paper delves into the realm of human resources analytics by conducting a comparative analysis of two machine learning models for predicting employee turnover. Leveraging a comprehensive dataset from the “Human Resources Data Repository,” the study employs Random Forest and Logistic Regression models to forecast turnover risk. Evaluation metrics including accuracy, precision, recall, F1-score, and ROC curves shed light on the models’ predictive capabilities. The results underline the Random Forest model's superiority in accuracy and precision, while the Logistic Regression model excels in recall. A balanced analysis of these models contributes insights into data-driven talent management strategies. This exploration encapsulates the evolving synergy between machine learning and HR, paving the way for informed decision-making in employee retention.