Preview

Informatics and education

Advanced search

Predicting student performance using machine learning tools

https://doi.org/10.32517/0234-0453-2023-38-4-28-43

Abstract

Digital assistants are increasingly penetrating various areas of human activity, including education. Today, they are no longer just automated systems or web applications that support and automate certain processes, including educational processes. Now they are more intelligent and more autonomous systems. Digital assistants play a special role in a student’s life, in a sense replacing the dean’s office, mentor, tutor, representatives of other university services and other elements of educational infrastructure. The digital support for the student is important and useful, especially in the first year during his adaptation to the environment of higher education, which is significantly different from the school one. It is at this point that the largest amount of students dropouts occurs due to academic failure. According to the authors, a digital assistant in the form of a mobile application that can predict learning outcomes and inform about it in time, can provide important support for the student and help him/her orient and adjust his/her behavior in case of a threat of a negative result. To solve the problems of creating a predictive model of student learning outcomes and a mobile application that implements it, as well as to conduct a pre-project study, the following methods and tools of mathematical statistics were used: k-means method, Kendall correlation method, Friedman’ test with Durbin—Conover posterior test, linear regression, logistic regression, categorical Bayesian classifier, random forest method, neural network (multilayer perceptron), non-parametric estimation of the Nadaraya—Watson regression function, STATISTICA 10.0 and Jamovi 2.2.5, Python libraries. As a result of the study, a mathematical model for predicting learning outcomes in disciplines based on current performance in e-learning courses was created. The accuracy of the model depends on the week of training in which it is applied and reaches 92,6 %. In the early stages (e. g., for week 7), the accuracy is at least 85 % and varies depending on the contingent of the student population and disciplines. As a result of the study, a mobile application was developed that implements a predictive model and other related functions to inform the student about his/her estimated educational success. The created predictive model is based on current performance data obtained from electronic courses and is capable of making accurate predictions, which allows it to be applied in practice online and through the mobile application to inform students.

About the Authors

Yu. Yu. Yakunin
Siberian Federal University
Russian Federation

Candidate of Sciences (Engineering), Docent, Head of the Basic Department of Intellectual Control Systems, School of Space and Information Technology



V. N. Shestakov
Siberian Federal University
Russian Federation

Candidate of Sciences (Philosophy), Associate Professor at the Department of Modern Educational Technologies, School of Education Science, Psycho logy and Sociology



D. I. Liksonova
Siberian Federal University
Russian Federation

Candidate of Sciences (Engineering), Associate Professor at the Basic Department of Intellectual Control Systems, School of Space and Information Technology



A. A. Danichev
Siberian Federal University
Russian Federation

Candidate of Sciences (Engineering), Associate Professor at the Basic Department of Intellectual Control Systems, School of Space and Information Technology



References

1. Alsariera Y. A., Baashar Y., Alkawsi G., Mustafa A., Alkahtani A. A., Ali N. A. Assessment and evaluation of different machine learning algorithms for predicting student performance. Computational Intelligence and Neuroscience. 2022;1:4151487. DOI: 10.1155/2022/4151487

2. Brahim G. B. Predicting student performance from online engagement activities using novel statistical features. Arabian Journal for Science and Engineering. 2022;47(8):10225–10243. DOI: 10.1007/s13369-021-06548-w

3. Toktarova V. I., Pashkova Y. A. Predictive analytics in digital education: Analysis and evaluation of students’ learning success. Siberian Pedagogical Journal. 2022;(1):97–106. (In Russian.) EDN: NSPMDR. DOI: 10.15293/1813-4718.2201.09

4. Almasri A., Celebi E., Alkhawaldeh R. S. EMT: Ensemble meta-based tree model for predicting student performance. Scientific Programming. 2019:1–13. DOI: 10.1155/2019/3610248

5. Shevchenko V. А. Prognostication of students progress on the basis of cluster analysis methods. Bulletin of Kharkov National Automobile and Highway University. 2015;(68):15–18. (In Russian.) EDN: UNSPAX

6. Aggarwal D., Mittal S., Bali V. Significance of nonacademic parameters for predicting student performance using ensemble learning techniques. International Journal of System Dynamics Applications. 2021;10(3):38–49. DOI: 10.4018/IJSDA.2021070103

7. Zohair L. M. A. Prediction of student’s performance by modelling small dataset size. International Journal of Educational Technology in Higher Education. 2019;(16):1–18. DOI: 10.1186/s41239-019-0160-3

8. Kupriyanov R. B., Zvonarev D. Yu. Improving the quality of the university students’ academic performance prediction model. Informatics and Education. 2021;36(9(328)):40–46. (In Russian.) EDN: WAAWTP. DOI: 10.32517/0234-04532021-36-9-40-46

9. Kupriyanov R. B., Zvonarev D. Yu. Development of the students’ educational success prediction model for universities. Artificial Intelligence and Decision Making. 2021;(2):11–20. (In Russian.) EDN: EENEFV. DOI: 10.14357/20718594210202

10. Deeva G., De Smedt J., Saint-Pierre C., Weber R., De Weerdt J. Predicting student performance using sequence classification with time-based windows. Expert Systems with Applications. 2022;(209):118182. DOI: 10.1016/j.eswa.2022.118182

11. Rusakov S. V., Rusakova O. L., Posokhina K. A. Neural network model of predicting the risk group for the accession of students of the first course. Modern Information Technologies and IT-Education. 2018;14(4):815–822. (In Russian.) EDN: JWGGFH. DOI: 10.25559/SITITO.14.201804.815-822

12. Ali R. H. Educational data mining for predicting academic student performance using active classification. Iraqi Journal of Science. 2022;63(9):3954–3965. DOI: 10.24996/ijs.2022.63.9.27

13. Li S., Liu T. Performance prediction for higher education students using deep learning. Complexity. 2021:1–10. DOI: 10.1155/2021/9958203

14. Poudyal S., Mohammadi-Aragh M. J., Ball J. E. Prediction of student academic performance using a hybrid 2D CNN model. Electronics. 2022;11(7):1–21. DOI: 10.3390/electronics11071005

15. Sood S., Saini M. Hybridization of cluster-based LDA and ANN for student performance prediction and comments evaluation. Education and Information Technologies. 2021;26(3):2863–2878. DOI: 10.1007/s10639-020-10381-3

16. Tsiakmaki M., Kostopoulos G., Kotsiantis S., Ragos O. Transfer learning from deep neural networks for predicting student performance. Applied Sciences. 2020;10(6):2145. DOI: 10.3390/app10062145

17. Liu Y., Fan S., Xu S., Sajjanhar A., Yeom S., Wei Y. Predicting student performance using clickstream data and machine learning. Education Sciences. 2023;13(1):1–17. DOI: 10.3390/educsci13010017

18. Conijn R., Van den Beemt A., Cuijpers P. Predicting student performance in a blended MOOC. Journal of Computer Assisted Learning. 2018;34(5):615–628. DOI: 10.1111/jcal.12270

19. Shukhman A. E., Parfenov D. I., Legashev L. V., Grishina L. S. Analysis and forecasting students’ academic performance using a digital educational environment. Higher Education in Russia. 2021;30(8-9):125–133. (In Russian.) EDN: QKRTNV. DOI: 10.31992/0869-3617-2021-30-8-9-125-133

20. Qiu F., Zhang G., Sheng X., Jiang L., Zhu L., Xiang Q., Jiang B., Chen P. Predicting students’ performance in e-learning using learning process and behaviour data. Scientific Reports. 2022;12(1):1–15. DOI: 10.1038/s41598-021-03867-8

21. Kotova E. E. Prediction of learning success in an integrated educational environment using online analytics tools. Computer Tools in Education Journal. 2019;(4):55–80. (In Russian.) EDN: GSJKDN. DOI: 10.32603/2071-2340-20194-55-80

22. Al-Kindi I., Al-Khanjari Z. Tracking student performance tool for predicting students EBPP in online courses. International Journal of Emerging Technologies in Learning (iJET). 2021;16(23):140–157. DOI: 10.3991/ijet.v16i23.25503

23. Pogrebnikov A. K., Shestakov V. N., Yakunin Yu. Yu. The influence of using parts of personal learning environment on student performance and learning motivation. Informatics and Education. 2020;(1(310)):42–50. (In Russian.) EDN: LTZJIQ. DOI: 10.32517/0234-0453-2020-35-1-42-50

24. Lewis H. G., Brown M. A generalized confusion matrix for assessing area estimates from remotely sensed data. International Journal of Remote Sensing. 2001;22(16):3223– 3235. DOI: 10.1080/01431160152558332

25. Nadaraya E. A. Nonparametric estimation of probability density and regression curve. Tbilisi, Tbilisi University; 1983. 194 p. (In Russian.)

26. Hyndman R. J., Koehler A. B. Another look at measures of forecast accuracy. International Journal of Forecasting. 2006;22(4):679–688. DOI: 10.1016/j.ijforecast.2006.03.001


Review

For citations:


Yakunin Yu.Yu., Shestakov V.N., Liksonova D.I., Danichev A.A. Predicting student performance using machine learning tools. Informatics and education. 2023;38(4):28-43. (In Russ.) https://doi.org/10.32517/0234-0453-2023-38-4-28-43

Views: 657


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


ISSN 0234-0453 (Print)
ISSN 2658-7769 (Online)