<![CDATA[Employee performance assessment is a critical step in achieving corporate objectives. However, this process often faces challenges such as a lack of accuracy and objectivity. To address these issues, this study proposes utilizing a machine learning-based classification model using the Decision Tree algorithm. The model is designed to classify employee performance based on four key aspects: productivity, skills, discipline, and work achievements. The research employs a supervised learning method with the Decision Tree algorithm, using employee performance data to build and evaluate the classification model. The objective of this study is to create an accurate, objective, and reliable assessment system that management can use to evaluate and improve human resource performance. The results indicate that the classification model achieves an accuracy level of 80%, demonstrating the model's capability to predict employee performance comprehensively. While this accuracy is considered satisfactory, the findings also suggest room for further development to enhance prediction accuracy and consistency, particularly in complex cases. The implementation of this model offers significant benefits in supporting strategic decision-making by company management and contributes to improving the quality of human resources. Keywords— Machine Learning, Employee performance,, Decision Tree]]>
Copyrights © 2025
