Employee attrition prediction using ensemble learning algorithms

Nowadays, due to various costs following the attrition of employees and the hiring of new people, managers prefer to have loyal employees in their company. On the other hand, the existence of a vast amount of data in the human resources departments has made it impossible for managers to analyze this information with traditional methods to make decisions. Data mining techniques using machine learning algorithms are new methods that can provide meaningful patterns and useful analyzes of a large amount of data in a short period of time. This study aims to create a predictive model for employee attrition using data mining techniques and machine learning algorithms. Based on this, company managers will be able to use this model to make smart decisions to retain current valuable employees and hire loyal employees in the future. Ensemble learning algorithms that combine several individual methods, usually considering each method's strengths and eaknesses, can provide better performance than the individual models separately. As a result of this work, the voting method, which is one of the ensemble learning models, had the highest accuracy of prediction, which was 92%.

Keywords:

employee's attrition , human resource management , data mining , machine learning , ensemble algorithms