An Improved Stacking Performance Classification Prediction Model in Blended Teaching of Advanced Mathematics

DOI: https://doi.org/10.62517/jike.202604121

Author(s)

Xiaoxu Xia, Meixue Liu*, Si Yuan, Lingna Li, Zhouyu Deng

Affiliation(s)

School of Sciences, Southwest Petroleum University, Chengdu, Sichuan, China *Corresponding Author

Abstract

Examination results not only directly reflect students’ learning outcomes but also indirectly indicate the effectiveness of teaching methods. However, traditional performance analysis primarily relies on summative evaluations of final exams, which are inherently delayed and insufficient to support individualized instruction. Consequently, performance prediction has become a prominent research focus in educational data mining. Students from six classes of the "Advanced Mathematics" course under a blended teaching model at a university are taken as research subjects in this study. A performance classification model based on hybrid sampling and an improved Stacking algorithm is proposed, which categorizes student performance into "Pass" or "Fail". Experimental results demonstrate that, compared with the traditional Stacking model(T-Stk), the improved model achieves increases of 0.43% in accuracy, 0.48% in precision, 0.23% in recall, and 1.57% in AUC.

Keywords

Performance Prediction; Stacking Fusion; Hybrid Sampling; Blended Teaching; Advanced Mathematics

References

[1]Harackiewicz J M, Durik A M, Barron K E, et al. The role of achievement goals in the development of interest: Reciprocal relations between achievement goals, interest, and performance. Journal of Educational Psychology, 2008, 100(1): 105. [2]Cortez P, Silva A M G. Using data mining to predict secondary school student performance. 2008. [3]Amra I A A, Maghari A Y A. Students performance prediction using KNN and Naïve Bayesian//2017 8th international conference on information technology (ICIT). IEEE, 2017: 909-913. [4]Zhang W, Zhou Y, Yi B. An interpretable online learner's performance prediction model based on learning analytics//Proceedings of the 11th International Conference on Education Technology and Computers. 2019: 148-154. [5]Younas M, Noor U, Zhou X, et al. COVID-19, students satisfaction about e-learning and academic achievement: Mediating analysis of online influencing factors. Frontiers in psychology, 2022, 13: 948061. [6]Ouajdouni A, Chafik K, Boubker O. Measuring e-learning systems success: Data from students of higher education institutions in Morocco. Data in Brief, 2021, 35: 106807. [7]Bossman A, Agyei S K. Technology and instructor dimensions, e-learning satisfaction, and academic performance of distance students in Ghana. Heliyon, 2022, 8(4). [8]Holicza B, Kiss A. Predicting and Comparing Students’ Online and Offline Academic Performance Using Machine Learning Algorithms. Behavioral Sciences, 2023, 13(4): 289. [9]Zhang W, Qin S, Yi B, et al. Study on learning effect prediction models based on principal component analysis in MOOCs. Cluster Computing, 2019, 22(6): 15347-15356. [10]Qiu F, Zhang G, Sheng X, et al.Predicting students’ performance in e-learning using learning process and behaviour data. Scientific Reports, 2022, 12(1): 453. [11]Hou J, Wen Y. Prediction of learners' academic performance using factorization machine and decision tree//2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData). IEEE, 2019: 1-8. [12]Puarungroj W, Boonsirisumpun N,Pongpatrakant P, et al. Application ofdata mining techniques for predicting student success in English exit exam//proceedings of the 12th international conference on ubiquitous information management and communication. 2018: 1-6. [13]Wu R, Yu Z. Relationship between university students’ personalities and e-learning engagement mediated by achievement emotions and adaptability. Education and Information Technologies, 2024, 29(9): 10821-10850. [14]Ekubo E A. Attributes of low performing students in e-learning systemusing clustering technique. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2019, 5(3).