Employee Attrition Analysis Using CatBoost
December 21, 2021 - July 11, 2022
Abstract. Almost everywhere, organizations or individuals can adopt technologies that can be supportive to make decisions and get insight from data: artificial intelligence is one of the most innovative technologies that are widely used to assist organizations in business strategies, organizational aspects, and people management. Employees are the nucleus of the organization. When employees leave an institution of their own volition, the company suffers greatly from various dimensions. In recent years, there has been a massive change in companies due to COVID-19; employees are getting fired or resigning voluntarily. It is a big issue to keep the productivity constant of a company or individual as HR has to spend a lot from the selection process to the training process. In these circumstances, minimizing the attrition rate is one of the primary concerns of the Human Resource department, which deals with staffing, development, and compensation. From this point of view, more research projects have been done through statistical analysis and applying various types of machine learning and data mining techniques such as Extreme Gradient Boosting, Random Forest, Naive Bayes, decision trees, etc. In this paper, a state-of-the-art boosting method, CatBoost, and a feature engineering process have been applied for detecting and analyzing employee attrition. Our detection system shows the utmost performance compared to the other existing systems and sorts out the significant reasons behind the attrition. It reveals the best recall rate of 0.89, with an accuracy of .8945.
