Human Resource Analytics for Enhancing Employee Performance through Machine Learning Techniques

Abstract

Human Resources (HR) onboarding is a critical step in integrating new employees into an organization. Effective onboarding can improve employee satisfaction, reduce turnover, and accelerate productivity. However, traditional methods for onboarding and predicting employee success are often limited to individual-level attributes, neglecting the complex network of relationships and team dynamics that influence an employee's experience. This study focuses on predicting employee performance using machine learning and deep learning techniques, with a particular emphasis on effective feature selection and preprocessing. The Employee Dataset, consisting of diverse demographic and organizational attributes, was preprocessed through normalization, outlier removal, and dimensionality reduction using PCA to ensure improved data quality and reduced redundancy. Deep Neural Network (DNN) model, was developed and evaluated. The results demonstrate that the proposed DNN model achieved a high accuracy of 96.25%, along with a precision of 98%, a recall of 97%, and an F1-score of 97%. These findings highlight the superior capability of the DNN in capturing complex patterns within employee data, making it a highly effective approach for enhancing prediction accuracy and supporting data-driven decision-making in employee performance management.