A Comparative Analysis of Logistic Regression and Support Vector Machine for Employee Churn Prediction

Employee Churn which is also called employee attrition, is a major problem faced by an organization. We know that employees are the valuable assets of any organization. There is a big challenge in front of the company whenever an employee leaves. For finding the new replacement, the company needs a lot of time. It has to spend money to train a new person. Plus, the new person who is hired usually needs some time to attain good form at their new job and start making money for the company. So, losing employees unexpectedly can be really costly for a company. This research study constructs a novel model to predict Employee Churn rate by using two robust machine learning algorithms: Logistic Regression and Support Vector Machine (SVM). The evaluation of the algorithms is done by using a dataset of employee records from a tech company. The study found that both the SVM and Logistic Regression algorithms performed well in predicting Employee Churn. The Logistic Regression algorithm achieved an accuracy of 87.52%, while Support Vector Machine had a slightly lower accuracy of 87.07<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>. Hence, the study concludes that the most reliable and accurate model to predict Employee Churn rate is Logistic Regression.