HR Analytics : Early Prediction of Employee Attrition using KPCA and Adaptive K-means based Logistic Regression

Abstract

The loss of employees may have a significant impact on an organization's ability to succeed. For a business, this may be too costly. To assess employee attrition costs, one must take into account the lifecycle of human resources, expertise loss, satisfaction levels among employees, and company culture. In this research, we used logistic regression to assess employee attrition. We can categories an employee who is leaving the organization based on the set of qualities in the data collection. In this paper, KPCA (Kernel Principal Component Analysis), Adaptive k-means, and the logistic regression (LR) technique are used. PCA improved clustering techniques and LR model performance compared to previous published research. Therefore, the proposed model is helpful in predicting employee attrition based on HR record data. The data may be used by organizations to figure out what alterations ought to be made in the direction of the workplace in order to keep most of their employees.