Application of Machine Learning Algorithms for Predicting Employee Attrition

Employers today are becoming more concerned about keeping their workforces, yet they mostly find it difficult to discover the actual causes of employee loss. Employee attrition can be caused by a variety of factors, including cultural and financial ones, but satisfaction levels are frequently under-looked. The goal of this research is to find patterns and trends by analysing the various factors that influence employee attrition, such as total working years, job satisfaction, age group and distance from home. The significant rise in the application of machine learning algorithms in recent years may provide new opportunities to improve the accuracy of employee attrition prediction. In this paper, we have applied two machine learning algorithms, Random Forest and Decision Tree Classifiers on a real dataset of an Australian company to predict employee attrition. Our findings highlight the superior performance of Random Forest over Decision Tree algorithm by achieving an accuracy value of 89.46%.

I. Introduction

Employee attrition, or turnover, is a pervasive issue faced by organizations across various industries. High attrition rates can lead to significant costs related to recruitment, training, and the loss of organizational knowledge. Moreover, frequent turnover can negatively impact employee morale and productivity, creating an unstable work environment. Understanding the factors that contribute to employee attrition and being able to predict which employees are at risk of leaving is crucial for organizations to implement effective retention strategies [1]–[3].