Predicting Accurate Employee Performance: An Evaluation of Regression Models

Accurately predicting employee performance is critical for organizations seeking to enhance productivity and decision-making. The conventional methodologies for machine learning such as linear regression (LR) and Decision Tree analysis have been utilized in prior research; but they frequently struggle to effectively capture the intricacies of employee behaviour. In this study, the various regression techniques, such as a random decision forest approach, gradient optimization, and neural network modelling, to predict employee performance are utilized. Gradient Boosting Classifier achieved the lowest Mean Squared Error (MSE) of 0.0211, while KNN and Neural Networks performed poorly with MSE values of 0.0383 and 0.0417, respectively. This research demonstrates the potential of advanced machine learning models, particularly Gradient Boosting, for improving predictive accuracy in employee performance assessments.