Classification and Prediction of Employee Attrition Rate using Machine Learning Classifiers

In today's time, employee attrition is a major problem faced by organisations. The most precious resource for a company is its workforce. They are the ones who bring value to the company both in terms of quantity and quality. A steady decline in the workforce due to retirement, death, or resignation is referred to as attrition. It is a matter of concern when employees leave their jobs of better opportunities but this leads the company to face its consequences. Employee attrition is like employee turnover. By understanding this concept, leaders can design smarter retention strategies to avoid it. This research uses a dataset to analyze attrition and find the reason why employee choose to resign. The training dataset is then analyzed for enabling effective data exploration. Machine Learning (ML) algorithms, such as Random Forest Classifier, Adaboost, XGBoost and ensemble stacking technique are considered. After data exploration, this study found Random Forest (RF) classifier as the best suited algorithm for this dataset with an accuracy of 87.41% and precision 88%. This study also concludes that the monthly income can be a reason behind employees leaving their job and finding better opportunities.