Predicting Student Success in Distance Education Utilizing Soft Matrix-Based Machine Learning via Moodle and Student Information Systems Data

Abstract

Machine learning has become an important tool for predicting student performance. This paper aims to create a dataset of the participation of some students who took Turkish Language, Atatürk’s Principles and History of Revolution, and English joint courses given via distance education at Istanbul Arel University to synchronous and asynchronous course activities for 14 weeks, and to predict the students’ success by employing fuzzy parameterized fuzzy soft k-nearest neighbor (FPFS-kNN) and the dataset. First, anonymized participation data from a 14-week lecture period is collected. Later, these data are processed to be used in machine learning. Two data sets are obtained from each raw dataset, whose class labels consist of two classes (pass/fail) and multi-class (letter grades). Then, FPFS-kNN and well-known/state-of-the-art machine learning algorithms are applied to the datasets. The performance results are compared using accuracy (Acc), precision (Pre), recall (Rec), macro F1-score (MacF1), and micro F1-score (MicF1) performance metrics. The results show that FPFS-kNN outperforms the other algorithms in binary pass–fail classification, achieving the highest accuracy with  (ING1),  (ATA1), and  (TDE1), while maintaining competitive F1-scores (up to  on TDE1). In the letter-grades datasets, performance decreased overall, with Boosted Tree reaching the best MicF1 (  on TDE2), yet FPFS-kNN still produced strong and stable results (  on TDE2,  on ATA2). These findings indicate that FPFS-kNN is highly effective in binary classification and competitive in multi-class problems. Finally, a discussion of performance results and the use of machine learning in predicting student achievement is provided.Machine learning has become an important tool for predicting student performance. This paper aims to create a dataset of the participation of some students who took Turkish Language, Atatürk’s Principles and History of Revolution, and English joint courses given via distance education at Istanbul Arel University to synchronous and asynchronous course activities for 14 weeks, and to predict the students’ success by employing fuzzy parameterized fuzzy soft k-nearest neighbor (FPFS-kNN) and the dataset. First, anonymized participation data from a 14-week lecture period is collected. Later, these data are processed to be used in machine learning. Two data sets are obtained from each raw dataset, whose class labels consist of two classes (pass/fail) and multi-class (letter grades). Then, FPFS-kNN and well-known/state-of-the-art machine learning algorithms are applied to the datasets. The performance results are compared using accuracy (Acc), precision (Pre), recall (Rec), macro F1-score (MacF1), and micro F1-score (MicF1) performance metrics. The results show that FPFS-kNN outperforms the other algorithms in binary pass–fail classification, achieving the highest accuracy with  (ING1),  (ATA1), and  (TDE1), while maintaining competitive F1-scores (up to  on TDE1). In the letter-grades datasets, performance decreased overall, with Boosted Tree reaching the best MicF1 (  on TDE2), yet FPFS-kNN still produced strong and stable results (  on TDE2,  on ATA2). These findings indicate that FPFS-kNN is highly effective in binary classification and competitive in multi-class problems. Finally, a discussion of performance results and the use of machine learning in predicting student achievement is provided.

Keywords

• Distance education
• Machine learning
• fpfs-matrices
• FPFS-kNN
• Student success prediction

References

1. [1] İşman, A., “Distance Education”, Pegem Academy Publishing, Ankara, Türkiye, (2011).
2. [2] Odabaş, H., “Internet–based distance education and departments of information and records management”, Turkish Librarianship, 17(1): 22–36, (2003).
3. [3] Ergin, İ., and Akseki, B., “Student information system used in graduate education”, Journal of Research in Education and Teaching, 1(2): 364–380, (2012). DOI: https://jret.elapublishing.net/makale/6068
4. [4] Gürkut, C., and Nat, M., “Important factors affecting student information system quality and satisfaction”, Eurasia Journal of Mathematics, Science and Technology Education, 14(3): 923–932, (2018). DOI: https://doi.org/10.12973/ejmste/81147
5. [5] Mohri, M., Rostamizadeh, A., and Talwalkar, A., “Foundations of Machine Learning”, London: The MIT Press, (2018).
6. [6] Moussawi, A., and Ibrahim, P., “Using machine learning to enhance ‘students’ assessment’ Moodle application”, Master’s Thesis, Arts, Sciences & Technology University, Beirut, (2020).
7. [7] Kliksoft, “Moodle Online Education”, https://www.kliksoft.net/moodle-lms/. Access date: 04.04.2023.
8. [8] Moodle, “The Moodle Story-Moodle-Online Education for Everyone”, https://moodle.com/about/the-moodle-story/. Access date: 24.04.2023.

9. [9] Lefebvre, G., Elghazel, H., Guillet, T., Aussem, A., and Sonnati, M., “A new sentence embedding framework for the education and professional training domain with application to hierarchical multi-label text classification”, Data & Knowledge Engineering, 150: 102281, (2024). DOI: https://doi.org/10.1016/j.datak.2024.102281
10. [10] Gerald, T., Tamames, L., Ettayeb, S., Le, H-Q., Paroubek, P., and Vilnat, A., “CQuAE: A new contextualized question answering corpus on education domain”, Data & Knowledge Engineering, 151: 102305, (2024). DOI: https://doi.org/10.1016/j.datak.2024.102305
11. [11] Koyuncu, İ., Kılıç, A. F., and Göksun, D. O., “Classification of students’ achievement via machine learning by using system logs in learning management system”, Turkish Online Journal of Distance Education, 23(3): 18–30, (2022). DOI: https://doi.org/10.17718/tojde.1137114
12. [12] Li, C., and Wang, B., “Fisher Linear Discriminant Analysis”, CCIS Northeastern University, 6, (2014).
13. [13] Altınsoy, F., “Predicting the success of distance education students using artificial intelligence techniques”, Master’s Thesis, Süleyman Demirel University, Isparta, (2019).
14. [14] Ho, A. D., Reich, J., Nesterko, S., Seaton, D. T., Mullaney, T., Waldo, J., and Chuang, I., “Person-course de-identification process, HarvardX and MITx: The first year of open online courses (HarvardX and MITx Working Paper No. 1),” (2014).
15. [15] Trevor, H., Tibshirani, R., and Friedman, J., “The Elements of Statistical Learning: Data Mining, Inference, and Prediction”, New York: Springer, (2009).
16. [16] Friedman, N., Geiger, D., and Goldszmidt, M., “Bayesian network classifiers”, Machine Learning, 29: 131–163, (1997). DOI: https://doi.org/10.1023/A:1007465528199
17. [17] Cortes, C., and Vapnik, V., “Support-vector networks,” Machine Learning, 20: 273–297, (1995). DOI: https://doi.org/10.1007/BF00994018
18. [18] Cornfield, J., “Joint dependence of the risk of coronary heart disease on serum cholesterol and systolic blood pressure: A discriminant function analysis”, Federation Proceedings, 21: 58–61, (1962). PMID: https://pubmed.ncbi.nlm.nih.gov/13881407
19. [19] Breiman, L., “Random forests,” Machine Learning, 45:5–32, (2001). DOI: https://doi.org/10.1023/A:1010933404324
20. [20] Aldous, D., “The continuum random tree I”, Annals of Probability, 19: 1–28, (1991). LINK: https://www.jstor.org/stable/2244250
21. [21] Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J., “Classification and Regression Trees”, Wadsworth: CRC Press, (1998). DOI: https://doi.org/10.1201/9781315139470
22. [22] Yıldız, O., Bal, A., and Gülseçen, S., “Statistical and clustering based rules extraction approaches for fuzzy model to estimate academic performance in distance education”, Eurasia Journal of Mathematics, Science and Technology Education”, 11(2): 391–404, (2015). DOI: https://doi.org/10.12973/eurasia.2015.1356a
23. [23] Azimi, S., Popa, C.-G., and Cucić, T., “Improving students’ performance in small-scale online courses–a machine learning-based intervention”, International Journal of Learning Analytics and Artificial Intelligence for Education, 2(2): 80–95, (2020). DOI: https://doi.org/10.3991/ijai.v2i2.19371
24. [24] Kalkan, Ö. K., and Coşguner, T., “Evaluation of the academic achievement of vocational school of higher education students through artificial neural networks”, Gazi University Journal of Science, 34(3): 851–862, (2021). DOI: https://doi.org/10.35378/gujs.819360
25. [25] Minaei-Bidgoli, B., Kashy, D. A., Kortemeyer, G., and Punch, W. F., “Predicting student performance: An application of data mining methods with an educational web-based system”, In EP. Innovations (Ed.) 33rd Annual Frontiers in Education (FIE’03), pp. T2A-13, Westminster: IEEE, (2003).
26. [26] Bognar, L., and Fauszt, T., “Different learning predictors and their effects for Moodle machine learning models,” In P. Baranyi, A. Esposito, M. Luimula, L. Oestreicher (Eds.), 11th IEEE International Conference on Cognitive Info Communications (CogInfoCom’20), pp. 405–410, Mariehamn: IEEE, (2020).
27. [27] Cox, D. R., “The Analysis of Binary Data”, London: Methuen & Co. Ltd., (1970).
28. [28] Kaensar, C., and Wongnin, W., “Analysis and prediction of student performance based on Moodle log data using machine learning techniques”, International Journal of Emerging Technologies in Learning, 18(10): 184–203, (2023). DOI: https://doi.org/10.3991/ijet.v18i10.35841
29. [29] Holicza, B., and Kiss, A., “Predicting and comparing students’ online and offline academic performance using machine learning algorithms”, Behavioral Sciences, 13(4): 289, (2023). DOI: https://doi.org/10.3390/bs13040289
30. [30] Vaarma, M., and Li, H., “Predicting student dropouts with machine learning: An empirical study in Finnish higher education”, Technology in Society, 76: 102474, (2024). DOI: https://doi.org/10.1016/j.techsoc.2024.102474
31. [31] Arévalo-Cordovilla, F. E., and Peña, M., “Comparative analysis of machine learning models for predicting student success in online programming courses”, Mathematics, 12(20): 3272, (2024). DOI: https://doi.org/10.3390/math12203272
32. [32] Shoaib, M., Sayed, N., Singh, J., Shafi, J., Khan, S., and Ali, F., “AI student success predictor: Enhancing personalized learning in campus management systems”, Computers in Human Behavior, 158: 108301, (2024). DOI: https://doi.org/10.1016/j.chb.2024.108301
33. [33] Wang, J., and Yu, Y., “Machine learning approach to student performance prediction of online learning”, PLOS ONE, 20(1): e0299018, (2025). DOI: https://doi.org/10.1371/journal.pone.0299018
34. [34] Ahmed, W., Wani, M. A., Plawiak, P., Meshoul, S., Mahmoud, A., and Hammad, M., “Machine learning-based academic performance prediction with explainability for enhanced decision-making in educational institutions”, Scientific Reports, 15: 26879, (2025). DOI: https://doi.org/10.1038/s41598-025-12353-4
35. [35] Marcolino, M. R., Porto, T. R., Primo, T. T., Targino, R., Ramos, V., Queiroga, E. M., Muñoz, R., and Cechinel, C., “Student dropout prediction through machine learning optimization: Insights from Moodle log data”, Scientific Reports, 15: 9840, (2025). DOI: https://doi.org/10.1038/s41598-025-93918-1
36. [36] Gourav, P., Pavan, G. Y., Kumar, R. A., and Kiranmai, M. G., “Predicting student success in online learning environment using machine learning”, IRACST – International Journal of Computer Networks and Wireless Communications, 15(2): 735–740, (2025). LINK: https://ijcnwc.2025.v15.i02.pp735-740
37. [37] Ramya, G., Chandra Lekha, N., Pranathi, P., and Sahana, P., “Machine learning for student performance forecasting in online examinations: A data-centric approach”, International Journal of Progressive Research in Engineering Management and Science, 5(6): 2534–2541, (2025). LINK: https://www.ijprems.com/ijprems-volume/volume-5-issue-6-june-2025
38. [38] Winarsih, W., Sutanto, H., and Widodo, A. P., “Implementation of the ensemble machine learning algorithm for student dropout prediction analysis”, Jurnal Sistem Informasi Bisnis, 15(2): 159–166, (2025). DOI: https://doi.org/10.14710/vol15iss2pp159-166
39. [39] Zerkouk, M., Mihoubi, M., and Chikhaoui, B., “Beyond classical and contemporary models: A transformative AI framework for student dropout prediction in distance learning using RAG, prompt engineering, and cross-modal fusion”. 17th International Conference on Education and New Learning Technologies, pp. 7118–7127, Palma, Spain, (2025).
40. [40] Anwar, S., “Predicting school dropout risk using machine learning models: a comparative study of random forest, gradient boosting, and neural network”, Journal of Economic, Technology and Business, 4(7): 595–605, (2025). DOI: https://doi.org/10.57185/jetbis.v4i6.193
41. [41] Poudyal, S., “A CNN-driven hybrid classification model to predict students’ academic performance”. 2025 ASEE Annual Conference & Exposition, Paper ID #48608, Montréal, Quebec, Canada, (2025).
42. [42] Amala, K. J., Rajeswari, D., and Venkatachalam, A., “Machine learning models for enhanced adaptive e-learning system design”, In Innovations and Challenges in Student Engagement in Higher Education (pp. 177–206). IGI Global Scientific Publishing, (2026).
43. [43] Islam, M. M., Yang, X., Debnath, R., Shoukarjya Saha, A., and Chi, M., “A generalized apprenticeship learning framework for capturing evolving student pedagogical strategies”. In A. I. Cristea, E. Walker, Y. Lu, O. C. Santos, S. Isotani (Eds.), Artificial Intelligence in Education, AIED 2025, Lecture Notes in Computer Science, vol 15879, pp. 393–408, Springer, Cham, (2025).
44. [44] Jabir, B., Hamzaoui, R., Rahali, E. A., and Falih, N., “A machine learning framework for early intervention in e-learning environments”, The EDP Audit, Control, and Security Newsletter, 70(12): 53–66, (2025). DOI: https://doi.org/10.1080/07366981.2025.2515737
45. [45] Memiş, S., Enginoğlu, S., and Erkan, U., “Numerical data classification via distance-based similarity measures of fuzzy parameterized fuzzy soft matrices”, IEEE Access, 9: 88583–88601, (2021). DOI: https://doi.org/10.1109/ACCESS.2021.3089849
46. [46] Memiş, S., Enginoğlu, S., and Erkan, U., “A classification method in machine learning based on soft decision-making via fuzzy parameterized fuzzy soft matrices”, Soft Computing, 26(3): 1165–1180, (2022). DOI: https://doi.org/10.1007/s00500-021-06553-z
47. [47] Memiş, S., Enginoğlu, S., and Erkan, U., “A new classification method using soft decision-making based on an aggregation operator of fuzzy parameterized fuzzy soft matrices”, Turkish Journal of Electrical Engineering and Computer Sciences, 30(3): 871–890, (2022). DOI: https://doi.org/10.55730/1300-0632.3816
48. [48] Memiş, S., Enginoğlu, S., and Erkan, U., “Fuzzy parameterized fuzzy soft k-nearest neighbor classifier”, Neurocomputing, 500: 351–378, (2022). DOI: https://doi.org/10.1016/j.neucom.2022.05.041
49. [49] Memiş, S., Arslan, B., Aydın, T., Enginoğlu, S., and Camcı, Ç., “A classification method based on Hamming pseudo-similarity of intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices”, Journal of New Results in Science, 10(2): 59–76, (2021).
50. [50] Memiş, S., Arslan, B., Aydın, T., Enginoğlu, S., and Camcı, Ç., “Distance and similarity measures of intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices and their applications to data classification in supervised learning”, Axioms, 12(5): 463, (2023). DOI: https://doi.org/10.3390/axioms12050463
51. [51] Enginoğlu, S., and Çağman, N., “Fuzzy parameterized fuzzy soft matrices and their application in decision-making”, TWMS Journal of Applied and Engineering Mathematics, 10(4): 1105–1115, (2020). DOI: http://jaem.isikun.edu.tr/web/index.php/archive/108-vol10no4/619
52. [52] Enginoğlu, S., and Arslan, B., “Intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices and their application in decision-making”, Computational and Applied Mathematics, 39(4): 325, (2020). DOI: https://doi.org/10.1007/s40314-020-01325-1
53. [53] Graf, S., and List, B., “An evaluation of open-source e-learning platforms stressing adaptation issues,” In Fifth IEEE International Conference on Advanced Learning Technologies (ICALT’05), pp. 163–165, IEEE, (2005).
54. [54] İstanbul Arel University, “Uzaktan Eğitim El Kitabı [Distance Learning Handbook]”, (2022). https://areluzem.arel.edu.tr/wp-content/uploads/2022/09/Uzaktan-Egitim-El-Kitabi.pdf. Access date: 02.05.2023.
55. [55] Çağman, N., Çıtak, F., and Enginoğlu, S., “Fuzzy parameterized fuzzy soft set theory and its applications”, Turkish Journal of Fuzzy Systems, 1(1): 21–35, (2010). LINK: https://www.researchgate.net/publication/229041420
56. [56] Karaaslan, F., “Intuitionistic fuzzy parameterized intuitionistic fuzzy soft sets with applications in decision making”, Annals of Fuzzy Mathematics and Informatics, 11(4): 607–619, (2016). LINK: http://www.afmi.or.kr/papers/2016/Vol-11_No-04/PDF/AFMI-11-4(607-619)-H-150813-1R1.pdf
57. [57] Memiş, S., Erduran, F. Ş., and Aydoğan, H., “Adaptive machine learning approaches utilizing soft decision-making via intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices”, PeerJ Computer Science, 11: e2703, (2025). DOI: https://doi.org/10.7717/peerj-cs.2703
58. [58] Fawcett, T., “An introduction to ROC analysis”, Pattern Recognition Letters, 27(8): 861–874, (2006). DOI: https://doi.org/10.1016/j.patrec.2005.10.010
59. [59] Cover, T. M., and Hart, P. E., “Nearest neighbor pattern classification”, IEEE Transactions on Information Theory, 13(1): 21–27, (1967). DOI: https://doi.org/10.1109/TIT.1967.1053964
60. [60] Keller, J. M., Gray, M. R., and Givens, J. A., “A fuzzy k-nearest neighbor algorithm”, IEEE Transactions on Systems, Man, and Cybernetics, (4): 580–585, (1985). DOI: https://doi.org/10.1109/TSMC.1985.6313426
61. [61] Friedman, J. H., “Greedy function approximation: A gradient boosting machine”, Annals of Statistics, 29(5): 1189-1232, (2001). LINK: https://www.jstor.org/stable/2699986
62. [62] Stone, M., “Cross-validatory choice and assessment of statistical predictions”, Journal of the Royal Statistical Society, Series B (Methodological), 36(2): 111–147, (1974). DOI: https://doi.org/10.1111/j.2517-6161.1974.tb00994.x
63. [63] Aydın, T., and Enginoğlu, S., “Interval-valued intuitionistic fuzzy parameterized interval-valued intuitionistic fuzzy soft sets and their application in decision-making”, Journal of Ambient Intelligence and Humanized Computing, 12(1): 1541–1558, (2021). DOI: https://doi.org/10.1007/s12652-020-02227-0
64. [64] Aydın, T., and Enginoğlu, S., “Interval-valued intuitionistic fuzzy parameterized interval-valued intuitionistic fuzzy soft matrices and their application to performance-based value assignment to noise-removal filters”, Computational and Applied Mathematics, 41(4): 192, (2022). DOI: https://doi.org/10.1007/s40314-022-01893-4
65. [65] Memiş, S., “Picture fuzzy parameterized picture fuzzy soft sets and their application in a performance-based value assignment problem to salt-and-pepper noise removal filters”, International Journal of Fuzzy Systems, 25(7): 2860–2875, (2023). DOI: https://doi.org/10.1007/s40815-023-01547-5
66. [66] Memiş, S., “Picture fuzzy soft matrices and application of their distance measures to supervised learning: Picture fuzzy soft k-nearest neighbor (PFS-kNN)”, Electronics, 12(19): 4129, (2023). DOI: https://doi.org/10.3390/electronics12194129
67. [67] Utku, A., and Akcayol, M. A., “Hybrid deep learning model for earthquake time prediction”, Gazi University Journal of Science, 37(3): 1172–1188, (2024). DOI: https://doi.org/10.35378/gujs.1364529
68. [68] Gürcan, Ö. F., Atıcı, U., and Beyca, Ö. F., “A hybrid deep learning-metaheuristic model for diagnosis of diabetic retinopathy”, Gazi University Journal of Science, 36(2): 693–703, (2023). DOI: https://doi.org/10.35378/gujs.919572