Automated Feature Engineering for Enhanced Employee Performance Prediction: A Machine Learning Approach

Organizations are now benefiting from various new technologies, enabling them to achieve their goals more efficiently in the short term. Technologies such as Artificial Intelligence, including machine learning and deep learning, play a crucial role in the development of organizations. Machine learning, in particular, helps convert extensive employee databases into actionable insights, facilitating better understanding. This study aims to explore the application of machine learning in organizations by utilizing different machine learning classifiers. Four machine learning classifiers were employed on an employee dataset including age, gender, education, income, environmental satisfaction, job satisfaction, relationship satisfaction, job involvement, performance rating, and experience. Each classifier predicts the overall performance of an employee based on accuracy scores. By comparing accuracy scores with the ROC curve, the study seeks to identify a suitable classifier for organizations. The results indicate that the RandomForest classifier achieved the highest accuracy score with a high AUC. This approach allows organizations to easily identify key performing employees and develop future tasks and plans accordingly. With the help of machine learning, organizations will predict employee performance which will determine the employee's nature. Various benefits are also having ML in Organizations like reducing manual error, improving network performance, and more security. Finally, this paper will give a clear insight into various classifiers of machine learning and its values to predict the performance of employees.