Research on the Construction and Application of Risk Prediction Model for University Management Students with Learning Difficulties Based on Machine Learning
DOI:
https://doi.org/10.54097/naw3n218Keywords:
Machine Learning, Intelligent Connected Vehicle Test Field Test Scenario, Fuzzy Comprehensive Evaluation Model, Virtual SimulationAbstract
The state has proposed to promote educational equity and the all-round development of students, but the existence of "students with learning difficulties" is contrary to the requirements of all-round development. The construction of a risk prediction model for students with learning difficulties is a teaching mode that can help students identify learning difficulties in advance, stimulate their interest in learning, reduce cognitive load, improve learning efficiency, and cultivate students' abilities and core literacy. This paper takes strengthening the education of the management major in universities as the core, and aims to promote educational equity and facilitate the all-round development of "students with learning difficulties". It proposes the construction and application research of a risk prediction model for students with learning difficulties in university management majors based on machine learning. In response to the problem of slow convergence speed in traditional machine learning This paper proposes an analysis model for the causes of learning difficulties among college management students based on the conjugate gradient method in machine learning, in order to predict the formation reasons of the difficulties of college management students. The factor quantification adopts the fuzzy comprehensive evaluation method. The experimental simulation results show that the system model shortens the training time, and the error between the predicted value and the actual value is zero. This model can be applied to the learning difficulties of English in higher vocational colleges Analysis and prediction of causes.
Downloads
References
[1] Jin, X. Q., Jiang, Q., & Ma, Z. Q., et al. (2023). Research on intelligent diagnosis model for college students with learning difficulties in the digital intelligence era. Modern Educational Technology, 33(11), 47–56.
[2] Li, M. R. (2024). Research on the current situation and improvement of learning outcomes of underachieving students in higher vocational colleges in the digital intelligence era. Journal of Hubei Open University, 44(5), 33–37.
[3] Li, Y. (2022). Research on the transformation countermeasures of students with learning difficulties in college English teaching in traditional Chinese medicine colleges from the perspective of "student-centeredness". Journal of Chengdu University of Traditional Chinese Medicine (Educational Science Edition), 24(4), 39–41, 70.
[4] Lin, X. Y. (2024). Action research on the transformation of junior high school students with English learning difficulties based on the PERMA model [Master’s thesis]. Guangzhou University. https://kns.cnki.net/kcms2/ article/abstract? v= 10. 27040/ d. cnki. ggzdu. 2024.000533.
[5] Zheng, P. (2024). Research on visual teaching strategies for improving the learning efficiency of students with learning difficulties [Master’s thesis]. Yunnan Normal University. https://kns.cnki.net/kcms2/article/abstract?v=10.27459/d.cnki.gynfc.2024.000507.
[6] Chen, Q. (2024). A case study on the motivation development of top and struggling students in the reading process of junior high school English reading classroom from the perspective of complex dynamic systems theory [Master’s thesis]. Central China Normal University. https://kns. cnki.net/kcms2/ article/ abstract? v=10. 27159/ d. cnki. ghzsu. 2024.002481.
[7] Li, G. S., Gao, T. G., Liu, X., et al. (2018). Research on prediction of students with learning difficulties based on extreme learning machine algorithm. Journal of Electrical and Electronic Teaching, 40(2), 69–75.
[8] Cui, X. C., Wang, J., Cui, X. M., et al. (2018). Attribution analysis of college students with learning difficulties based on ID3 algorithm. Journal of Electrical and Electronic Teaching, 40(2), 69–75.
[9] Guo, Q. C. (2024). Structural design and optimization of copper-based composites based on machine learning and multi-objective optimization [Master’s thesis]. Xi’an University of Science and Technology. https://kns.cnki.net/kcms2/ article/ abstract?v=10.27398/d.cnki.gxalu.2024.000820.
[10] Deng, J., Chen, K. Y., Liu, S. Y., et al. (2025). Carbon emission prediction method for vessels on the Yangtze River trunk line based on MPA-BP. Journal of Wuhan University of Technology (Traffic Science and Engineering Edition). Advance online publication. https://kns.cnki.net/kcms/ detail/ detail.aspx?dbcode=CJFD&dbname=CJFDLAST2025&filename=WHJT20250325002.
[11] Chen, X. C., Ji, Z. R., Zheng, Y., et al. (2025). DBO-machine learning-based activity guide vane abrasion prediction model. Journal of Huazhong University of Science and Technology (Natural Science Edition). Advance online publication. https://doi.org/10.13245/j.hust.250405.
[12] Wu, Y. M., Zhang, C. L., & Zhang, H. X. (2025). Slope deformation prediction research based on hippopotamus algorithm optimized machine learning model. Water Resources and Hydropower Technology (Bilingual Edition). Advance online publication. https://kns.cnki.net/kcms/ detail/ 10. 1746.TV.20250315.1157.006.html.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

