Predicting Employee Performance Using Machine Learning

Abstract

Human resource (HR) is the department inside an organization that is in charge of managing and administering the human capital or workforce. Human resources specialists are involved in many elements of the employee lifecycle, including recruitment and selection, training and development, performance management, compensation and benefits, employee relations, and overall organizational workforce planning. In today's changing and competlttve business environment, accurately predicting employee performance plays an important role in strategic decision making, resource allocation, and talent management. With the increasing awareness and use of machine learning techniques and the availability of vast amounts of employee data, many organizations can use this data to create prediction models that identify employees with high potential for success. This report focuses on using machine learning to predict employee performance with the help of various factors including promotion data, number of awards won, nature and level of schooling, years of experience, average training score, and number of trainings completed. Previous research by lather, Anu and Malhotra, Rucluka and Smgh, Prabhjot and Mtttal, Sarthak (20 19) has highlighted the promising outcomes of machine learning algorithms in the domain of human resource management. Machine learning models can uncover patterns and provide accurate predictions by analyzing historical data, including employee demographics, previous performance, and training records. In our study, we explore the predictive power of variables such as the number of awards won, number of trainings completed, level of education, length of service, previous year rating, and total KPis met during the employee's tenure.