Email this article 
Increasing the accuracy of the model for predicting the performance of university students
- Authors: Liksonova D.I.1, Danichev A.A.1, Shestakov V.N.1, Yakunin Y.Y.1
-
Affiliations:
- Siberian Federal University
- Issue: Vol 31, No 4 (2025)
- Pages: 215-224
- Section: Information technologies in education
- Published: 15.04.2025
- URL: https://journals.eco-vector.com/1684-6400/article/view/702292
- DOI: https://doi.org/10.17587/it.31.215-224
- ID: 702292
Cite item
Open Access
Access granted
Subscription or Fee Access
Abstract
This paper discusses approaches to preparing educational data on students’ learning outcomes to improve the accuracy of predicting their academic performance over a given period. The rules for checking initial data for using them in a forecasting model are considered, implemented, and investigated. The rules help to work with poor-quality initial data and improve the accuracy of modeling. Modeling of students’ learning outcomes is based on a nonparametric estimate of the Nadaraya-Watson regression function. The article presents some fragments of computational experiments that show acceptable results from a practical point of view.
About the authors
D. I. Liksonova
Siberian Federal University
Author for correspondence.
Email: liksonovadi@yandex.ru
Cand. Sc., Assistant Professor
Russian Federation, KrasnoyarskA. A. Danichev
Siberian Federal University
Email: adanichev@sfu-kras.ru
Cand. Sc., Assistant Professor
Russian Federation, KrasnoyarskV. N. Shestakov
Siberian Federal University
Email: vshestakov@sfu-kras.ru
Cand. Sc., Assistant Professor
Russian Federation, KrasnoyarskYu. Yu. Yakunin
Siberian Federal University
Email: yakuninyy@mail.ru
Cand. Sc., Assistant Professor
Russian Federation, KrasnoyarskReferences
- Bognar L. Predicting Student Attrition in University Courses, Machine Learning Educational Sciences, Khine, M. S. (eds), Springer, Singapore, 2024, pp. 129—157.
- Yakunin Yu. Yu., Shestakov V. N., Liksonova D. I., Danichev A. A. Predicting student learning outcomes using machine learning tools, Informatika i obrazovanie, 2023, vol. 38, no. 4, pp. 28—43 (in Russian).
- Toktarova V. I., Pashkova Yu. A. Predictive analytics in digital education: analysis and assessment of student learning success, Sibirskij pedagogicheskij zhurnal, 2022, no. 1, pp. 97—106 (in Russian).
- Popova N. A., Egorova E. S. Intelligent analysis of educational data to predict the performance of university students, Izvestiya Kabardino-Balkarskogo nauchnogo centra RAN, 2023, no. 2 (112), pp. 18—29 (in Russian).
- Rusakov S. V., Rusakova O. L., Posohina K. A. Neural network model for predicting risk groups based on academic performance of first-year students, Sovremennye’ informacionnye tekhnologii i IT-obraz.ovanie, 2018, vol. 14, no. 4, pp. 815—822 (in Russian).
- Budaeva A. A. Forecasting personal academic performance of students at university, IT-Tekhnologii: razvitie i prilozheniya, XV Ezhegodnaya Mezhdunarodnaya nauchnotekhnicheskaya konferen- ciya, 2018, pp. 9—16 (in Russian).
- Al-Shehri H. et al. Student performance prediction using support vector machine and k-nearest neighbor, IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE), IEEE, 2017, pp. 1—4.
- Apatova N. V., Gaponov A. I., Majorova A. N. Predicting student performance based on fuzzy logic, Sovremennye naukoem- kie tekhnologii, 2017, no. 4, pp. 7—11 (in Russian).
- Proshkina E. N., Balashova I. Yu. Analysis and forecasting of student performance based on a radial basis neural network, Tekhnicheskie nauki: tradicii i innovacii: materialy III Mezhdunar. nauch. konf., 2018, pp. 24—28 (in Russian).
- Kaledin O. E., Kaledina E. A., Shcherbakov D. V. Predicting the academic performance of university students based on collaborative filtering algorithms, Vestnik komp’yuternyh i informacionnyh tekhnologij', 2023, vol. 20, no. 2 (224), pp. 37—43 (in Russian).
- Kosyakin Yu. V. Predicting the current and long-term performance of distance education students based on regression models, Gumanitarnoe obrazovanie v paradigme slozhnosti: sbornik nauchnyh statej, 2016, pp. 14—44 (in Russian).
- Ohkawauchi T., Tanaka E. Predicting Student Dropout Risk Using LMS Logs, IIAI Letters on Institutional Research, 2024, vol. 4, 8 p.
- Zheleznov M. M. Methods and technologies for processing big data, Moscow, Publishing house of MISI — MGSU, 2020, 46 p (in Russian).
- Belonozhko P. P., Karpenko A. P., Hramov D. A. Analysis of educational data: directions and prospects for application, NAUKOVEDENIE, 2017, vol. 9, no. 4 (in Russian).
- Ryzhenkova K. V. Methods for recovering missing data when conducting statistical research, Intellekt. Innoveicii. Investicii, 2012, no. 3, pp. 127—133 (in Russian).
- Pogrebnikov A. K., Shestakov V. N., Yakunin Yu. Yu. The influence of the use of elements of a personal educational environment on students’ performance and their motivation to learn, Informatika i obrazovanie, 2020, no. 1 (310), pp. 42—50 (in Russian).
- Nadaraya E. A. Nonparametric probability density and regression curve estimation, Tbilisi, Publishing house of TGU, 1983. 194 p (in Russian).
- Sign test, available at: https://en.wikipedia.org/wiki/ Sign_test (date of access: 15.04.24).
- Fisher’s angular transformation, available at: https:// studizba.com/lectures/psihologiya/matematicheskie-metody-v- psihologii/17482-uglovoe-preobrazovanie-fishera.html (date of access: 25.03.24) (in Russian).
Supplementary files
