A Study of Math Grade Prediction Models Combining Boosting and Decision Tree C5.0

• Published in: 2024 7th International Conference on Education, Network and Information Technology (ICENIT) pp. 181 - 186
• Main Author: Tang, Mohan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.08.2024
• Subjects: Accuracy; achievement; Analytical models; Boosting; decision tree C5.0; Decision trees; Education; Machine learning algorithms; math; Mathematical models; prediction; Prediction algorithms; Predictive models; Random forests
• DOI: 10.1109/ICENIT61951.2024.00040

With the speedy prosperity of science and technology, machine learning algorithms are commonly utilized in the field of classification and prediction due to their powerful data mining ability. Aiming at the problem of students' poor math performance, the study proposes a model that integrates Boosting algorithm into Decision Tree C5.0, and extracts the key factors affecting students' math performance using factor analysis. And the two were combined to construct a math achievement prediction model that integrates Boosting and Decision Tree C5.0. Subsequently, the performance of the model fusing Boosting and Decision Tree C5.0 was compared and analyzed with other models, and it was found that the accuracy and precision of the model were 0.968 and 0.912, separately, which were better than the comparison models. Then, the capability of the mathematical achievement prediction model was analyzed in comparison with other models, and the outcomes indicated that the mean prediction accuracy of the prediction model was 92.9%, which was significantly better than the comparison model. The above outcomes tell that the model raised in the study outperforms the comparison model considerably and is effective in predicting students' performance and providing a reference basis for math teachers to adjust their teaching strategies, which in turn improves students' motivation to learn.