<![CDATA[This study investigates the optimization of the ID3 algorithm for academic performance analysis using the Ant Colony Optimization (ACO) method. The primary research problem addressed is the inefficiency and overfitting of traditional ID3 in complex and noisy datasets. Therefore, the ACO method is integrated to enhance the ID3 structure, improving classification accuracy and computational efficiency. The research objectives include developing a decision tree model based on assignment, mid-term, and final exam scores for student performance evaluation. The method combines ID3's decision-making capabilities with ACO's optimization process, which uses pheromone trails to find optimal paths in constructing the decision tree. Temporary results show that the ACO-ID3 model achieves an accuracy of 85% with improved consistency and lower variability compared to the traditional ID3 model, which has an accuracy of 89% but higher variability; this indicates that while traditional ID3 may slightly outperform in accuracy, the ACO-ID3 model provides more stable and reliable performance across different data subsets. The study concludes that ACO-ID3 is a practical and effective tool for academic performance analysis, particularly in cases requiring consistent and reliable classification]]>
Copyrights © 2024
