Peng Zhao1,2,*, Junye Yang1,2, Rongmu Cai1,2, Jia Gao1,2
1School of Computer Science and Technology, Taiyuan Normal University, Jinzhong 030619, Shanxi, China.
2Shanxi Key Laboratory of Intelligent Optimization Computing and Blockchain Technology, Taiyuan Normal University, Jinzhong 030619, Shanxi, China.
*Corresponding author: Peng Zhao
Abstract
As the rapid development of digitalization has led to profound changes in the field of education and the integration of artificial intelligence technology, early education is facing problems such as a lack of funds and uneven teacher resources. Although the country has promoted artificial intelligence in education to improve hardware, teachers, and students lack application capabilities and lack guidance programs. This study predicts student scores based on a multi-layer perceptron model, aiming to explore the application of artificial intelligence in the field of educational evaluation. It can provide teachers with forward-looking teaching references to adjust strategies and implement teaching in accordance with students' aptitude, help students discover weak links and plan their learning, provide new ideas for solving educational practice problems, promote the development of educational artificial intelligence, and provide empirical support for achieving high-quality and equitable education.
References
[1] Fan Z, Gou J, Weng S. Complementary CatBoost based on residual error for student performance prediction. Pattern Recognition. 2025;161:111265.
[2] Borna MR, Saadat H, Hojjati AT, et al. Analyzing click data with AI: implications for student performance prediction and learning assessment. In: Frontiers in Education. Frontiers Media SA; 2024. p. 1421479.
[3] Luo Z, Mai J, Feng C, et al. A method for prediction and analysis of student performance that combines multi-dimensional features of time and space. Mathematics. 2024;12(22):3597.
[4] Junejo NUR, Huang Q, Dong X, et al. SAPPNet: students’ academic performance prediction during COVID-19 using neural network. Scientific Reports. 2024;14(1):24605.
[5] Wang K. Optimized ensemble deep learning for predictive analysis of student achievement. Plos One. 2024;19(8):e0309141.
[6] Dien TT, Luu SH, Thanh-Hai N, et al. Deep learning with data transformation and factor analysis for student performance predic-tion. International Journal of Advanced Computer Science and Applications. 2020;11(8).
[7] Meng F. Research on text recognition methods based on artificial intelligence and machine learning. Advances in Computer and Communication. 2023;4(5):340-344.
[8] Khin Shin Thant, Ei Theint Theint Thu, Myat Mon Khaing, Khin Lay Myint, Hlaing Htake Khaung Tin. Evaluation of student academic performance using Naïve Bayes classifier. Advances in Computer and Communication. 2020;1(1):46-52.
[9] Xu H, Deng Y. Dependent evidence combination based on Shearman coefficient and Pearson coefficient. IEEE Access. 2017;6:11634-11640.
[10] Armstrong RA. Should Pearson's correlation coefficient be avoided? Ophthalmic and Physiological Optics. 2019;39(5):316-327.
[11] Adler J, Parmryd I. Quantifying colocalization by correlation: the Pearson correlation coefficient is superior to the Mander's overlap coefficient. Cytometry Part A. 2010;77(8):733-742.
[12] Gardner MW, Dorling SR. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric Environment. 1998;32(14-15):2627-2636.
[13] Adeli H, Yeh C. Perceptron learning in engineering design. Computer-Aided Civil and Infrastructure Engineering. 1989;4(4):247-256.
[14] Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review. 1958;65(6):386.
[15] Spring J. Research on globalization and education. Review of Educational Research. 2008;78(2):330-363.
How to cite this paper
Prediction of Student Performance Based on MPL
How to cite this paper: Peng Zhao, Junye Yang, Rongmu Cai, Jia Gao. (2025) Prediction of Student Performance Based on MPL. Advances in Computer and Communication, 6(1), 27-34.
DOI: http://dx.doi.org/10.26855/acc.2025.01.005