A Study on Employee Performance Prediction Using Machine Learning and HR Analytics at Bevcon Wayors Pvt. Ltd

Abstract

Employee performance is a key factor influencing organizational productivity, operational efficiency, and long-term business success. Traditional performance appraisal methods often rely on subjective evaluations, making it difficult to identify performance trends and support data-driven decision-making. The emergence of Human Resource (HR) Analytics and Machine Learning (ML) has enabled organizations to analyze large volumes of employee data and generate accurate predictions regarding workforce performance. This study focuses on employee performance prediction using Machine Learning and HR Analytics at Bevcon Wayors Pvt. Ltd. The research aims to develop a predictive framework that analyzes employee-related attributes such as attendance, work experience, training participation, performance ratings, project completion, productivity, and behavioral indicators to classify employee performance levels. The study employs data preprocessing, feature selection, and supervised machine learning algorithms including Decision Tree, Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) to identify the most suitable predictive model. Model performance is evaluated using standard metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The findings are expected to assist HR managers in identifying highperforming employees, recognizing individuals requiring additional support or training, improving workforce planning, and optimizing performance management strategies. By integrating HR analytics with machine learning techniques, the proposed approach contributes to objective, data-driven human resource decisionmaking while enhancing employee productivity and organizational effectiveness at Bevcon Wayors Pvt. Ltd.