The prediction of student performance is an important research direction of educational data mining. However, current predictive models often fail to sufficiently reflect the learning process and lack a quantitative analysis of the impact of different predictors. In this study, we collected the learning data of 395 students enrolled in the Python Programming course offered by Chongqing University of Posts and Telecommunications, and developed a model based on the random forest algorithm to predict and analyze student performance. Evaluation results indicate that the model can accurately predict student performance (R² = 0.55, RMSE = 4.68 points and MAE = 3.61 points). Moreover, an importance analysis of the predictors revealed that the score of the 2nd unit test had the greatest impact on student performance, followed by the score of the 4th unit test and the average score of homework. This study provides guidance for early warning of students' learning difficulties and for continuous curriculum enhancement, thereby serving as a reference for enhancing teaching quality.

Xiaobo Zhu. Prediction and Analysis of University Student Performance Based on Machine Learning. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 8: 74-78. https://doi.org/10.25236/AJCIS.2024.070811.

[1] Zhang Z, Chu Z. Student achievement prediction model based on XGBoost and SHAP feature analysis [J]. Informatization Research, 2024, 50(03): 34-40. 

[2] Cao H J, Xie J. LSTM-based learning achievement prediction and its influencing factors [J]. Journal of Beijing University of Posts and Telecommunications (Social Sciences Edition), 2020, 22(06): 90-100.

[3] Jembere E, Rawatlal R, Pillay A W. Matrix factorisation for predicting student performance[C]. In 7th World Engineering Education Forum, 2017: 513-518. 

[4] Ren Z, Ning X, Lan A S, et al. Grade Prediction with Neural Collaborative Filtering[C]. In 2019 IEEE International Conference on Data Science and Advanced Analytics, 2019: 1-10.

[5] Zhang F, Chen J J. Overview of learning data features application to student performance prediction [J]. Software Engineering, 2023, 26(10): 1-4.

[6] Li K W. Grade prediction of university student based on machine learning[J]. Computer Era, 2023, 12: 220-223.

[7] Liu T, Qi H R, Ni W J. Multilayer feature fusion based model for prediction student academic performance[J]. Computer Engineering and Design, 2023, 44(10): 2973-2978.

[8] Breiman L. Random forests [J]. Machine Learning, 2001, 45(1): 5-32.

[9] Yang R M, Zhang G L, Liu F, et al. Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem[J]. Ecological Indicators, 2016, 60: 870-878.

[10] Liu B P, Fan T C, Yang H. Research on application of early warning of student’s achievement based on data mining [J]. Journal of Sichuan University (Natural Science Edition), 2019, 56(02): 267-272.