Volume 4,Issue 2
Student Academic Performance Prediction: A Method Based on XGBoost Multi-Modal Feature Fusion
In the realm of educational management, predicting stu- dent academic performance is challenged by the complexity of multi- factor influences and limitations in model generalization. This study introduces a multi-modal feature fusion mechanism based on Gradient Boosting Decision Trees (XGBoost) for student performance prediction. The mechanism begins with a preprocessing module to clean the dataset, handle missing values, and encode categories to extract reliable features such as student demographics, study habits, and parental involvement. An embedding layer then converts categorical features into continuous vectors. A fusion layer employs an attention mechanism to dynamically adjust weights among feature groups, addressing biases from fixed weights in traditional ensemble methods. The XGBoost core tree boosting algorithm is used for training and iterative optimization, with the output layer generating performance prediction scores. Training incorporates cross-entropy loss combined with L2 regularization to enhance robustness and prevent overfitting, thereby improving predic- tion accuracy and generalization on educational datasets. Experimental results on a Kaggle student performance dataset demonstrate superior performance compared to baselines, achieving over 85% accuracy through 10-fold cross-validation. This approach provides a robust framework for early intervention in student performance management.
[1] Lou Y, Colvin KF, 2025, Performance Prediction Using Educational Data Mining Techniques: A Comparative Study. Discover Education, 4: 112.
[2] Yang D, Ma J, 2024, Student Performance Prediction with Regression Approach and Data Generation. Applied Sciences, 14(3): 1148.
[3] Alsariera YA, Baashar Y, Alkawsi G, et al., 2022, Assessment and Evaluation of Different Machine Learning Algorithms for Predicting Student Performance. Computational Intelligence and Neuroscience, 4151487.
[4] Alsariera YA, Adeyemo V, Balogun A, 2022, AI meta-learners and extra-trees algorithm for the detection of phishing websites. IEEE Access, 8: 142532-142542.
[5] Khairy D, Alharbi N, Amasha MA, et al., 2024, Prediction of student exam performance using data mining classification algorithms. Education and Information Technologies, 29: 21621-21645.
[6] Holicza B, Kiss A, 2023, Predicting and comparing students' online and offline academic performance using machine learning algorithms. Behavioral Sciences, 13(4): 289.
[7] Okur E, Aslan S, Alyuz N, et al., 2018, Role of socio-cultural differences in labeling students' affective states. In Artificial Intelligence in Education, pp. 367-380.
[8] Chaka C, 2022, Educational data mining, student academic performance prediction, prediction methods, algorithms and tools: an overview of reviews. Journal of E-Learning and Knowledge Society, 18(2): 58-69.
[9] Li C, Li M, Huang C, et al., 2023, Educational data mining in prediction of students' learning performance: A scoping review. In IFIP Advances in Information and Communication Technology, vol. 685, pp. 361-372.
[10] Xiao W, Ji W, Hu J, 2022, A survey on educational data mining methods used for predicting students' performance. Engineering Reports, 4(5): e12482.
[11] Zhang Y, An R, Cui L, et al., 2021, Educational data mining techniques: Student performance prediction in intelligent tutoring systems. Journal of Educational Data Mining, 13(2): 1-29.
[12] Chango W, Cerezo J, Sanchez C, Arriaga I, Escobar R, 2024, Multi-source and multimodal data fusion for predicting academic performance in blended learning university courses. Computers & Electrical Engineering, 89: 106908.
[13] Zou W, Zhong W, Du J, et al., 2025, Prediction of student academic performance utilizing a multi-model fusion approach in the realm of machine learning. Applied Sciences, 15(7): 3550.
[14] Adefemi KO, Mutanga MB, Jugoo V, 2025, Hybrid deep learning models for predicting student academic performance. Mathematical and Computational Applications, 30(3): 59.
[15] Stöhr C, Ou AW, Malmström H, 2024, Perceptions and usage of AI chatbots among students in higher education across genders, academic levels and fields of study. Computers and Education: Artificial Intelligence, 7: 100259.