Predictive model of employee attrition based on stacking ensemble learning

Since human resource is the most important resource of a company, employee attrition is an important agenda from the company's point of view. However, employee attrition occurs due to various reasons, and it is difficult for the HR manager or the leader of each department to know these signs in advance. Employee attrition results in considerable burdens and losses of the organization due to a variety of reasons such as interruption of ongoing tasks, cost of employee re-employment and retraining, and risk of leaking core technologies and know-hows. Therefore, in this study, we propose a model for predicting employee attrition so that we can take measures for talent management which in the past, has been carried out ex post. In this study, a predictive model was constructed based on 30 variables - that affect employee attrition - from the 'IBM HR Analytics Employee Attrition & Performance data', which consists of 1,470 records. To this end, a total of eight predictive models, including Logistic Regression, Random Forest, XGBoost, SVM, Artificial Neural Network model and ensemble model, were built and their performance was evaluated. In addition, when the impact of variables on employee attrition was analyzed, variables such as environmental satisfaction, overtime work, and relationship satisfaction were found to be the biggest contributors.