Subject. The article considers the application of machine learning methods to analyze students' academic performance. Objectives. The aims are to identify factors influencing the academic performance of students, detect hidden patterns, useful and interpretable knowledge about the results of educational process and its participants, using the intellectual analysis of educational data. Methods. The study rests on methods of econometric modeling, multidimensional classification, and big data clustering. Results. The developed models of intellectual analysis of educational data enable to perform a comparative analysis of students and forecast the level of student’s mastering an educational program, depending on factors like the total score of entrance tests, average score of academic performance, basis and form of education, course, the level of training, student’s gender and age. Conclusions. The results of the application of machine learning methods to analyze academic performance will help differentiate effective teaching methods and technologies for groups of students with different levels of academic results, timely take corrective actions regarding students from risk group. Eventually, this will contribute to retention of students and improvement of the educational process quality.
Keywords: educational data, data mining, academic performance, modeling, machine learning
References:
Baker R.S., Inventado P.S. Educational Data Mining and Learning Analytics. In: Larusson J., White B. (eds) Learning Analytics. Springer, New York, 2014, pp. 61–75. URL: Link
Siti Khadijah Mohamad, Zaidatun Tasir. Educational Data Mining: A Review. Procedia – Social and Behavioral Sciences, 2013, vol. 97, pp. 320–324. URL: Link
Zamkov O.O., Peresetskii A.A. [Russian Unified National Exams (UNE) and academic performance of ICEF HSE students]. Prikladnaya ekonometrika = Applied Econometrics, 2013, no. 2, pp. 93–114. URL: Link (In Russ.)
Zakharova I.G. [Machine Learning Methods of Providing Informational Management Support for Students’ Professional Development]. Obrazovanie i nauka =The Education and Science Journal, 2018, vol. 20, no. 9, pp. 91–114. (In Russ.) URL: Link
Zakharova I.G. [“Big Data and Educational Process Management”]. Vestnik Tyumenskogo gosudarstvennogo universiteta. Gumanitarnye issledovaniya. Humanitates = Tyumen State University Herald. Humanities Research. Humanitates, 2017, vol. 3, no. 1, pp. 210–219. (In Russ.) URL: Link
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]. Sovremennye informatsionnye tekhnologii i IT-obrazovanie = Modern Information Technology and IT-education, 2018, no. 4, pp. 815–822. (In Russ.) URL: Link
Pomyan S.V., Belokon' O.S. [Forecast of the results of academic performance of university students based on Markov processes]. Vestnik Vyatskogo gosudarstvennogo universiteta = Herald of Vyatka State University, 2020, no. 4, pp. 63–73. URL: Link (In Russ.)
Salal Ya.K., Abdullaev S.M. [Monitoring of the education quality and implementing of individual learning: Demonstration of approaches and educational data mining algorithms]. Izvestiya YuFU. Tekhnicheskie nauki = Izvestiya SFedU. Engineering Sciences, 2020, no. 3, pp. 112–122. (In Russ.) URL: Link
Fiofanova O.A. Analiz bol'shikh dannykh v sfere obrazovaniya: metodologiya i tekhnologii [Big data analysis in education: Methodology and technology]. Moscow, Delo Publ., 2020, 200 p.
Chastikova V.A., Pseush A.G. [Data mining in the construction of individual educational trajectories]. Vestnik Adygeiskogo gosudarstvennogo universiteta. Seriya 4: Estestvenno-matematicheskie i tekhnicheskie nauki = Bulletin of Adyghe State University. Series Natural-Mathematical and Technical Sciences, 2021, no. 2, pp. 66–71. (In Russ.) URL: Link
Kotova E.E. [Prediction of Learning Success in an Integrated Educational Environment Using Online Analytics Tool]. Komp'yuternye instrumenty v obrazovanii = Computer Tools in Education, 2019, no. 4, pp. 55–80. (In Russ.) URL: Link
Belonozhko P.P., Karpenko A.P., Khramov D.A. [Analysis of educational data: Directions and prospects of application]. Naukovedenie, 2017, vol. 9, no. 4. (In Russ.) URL: Link
Chernyshova N.A. [Correlation between the results of the unified State examination and achievement of students in an agricultural university]. Vestnik Nizhegorodskogo universiteta im. N.I. Lobachevskogo. Seriya: Sotsial'nye nauki = Vestnik of Lobachevsky State University of Nizhny Novgorod. Social Sciences, 2017, no. 1, pp. 171–177. URL: Link (In Russ.)
Shirinkina E.V. [Methods of data mining and educational analytics]. Sovremennoe obrazovanie, 2022, no. 1. (In Russ.) URL: Link
Kharlamova I.Yu. [The prediction of academic performance of students of the first course by results of unified State exam]. Bazis = Basis, 2017, no. 1, pp. 57–59. URL: Link (In Russ.)
Toktarova V.I., Popova O.G. [An analysis of educational data on the correlation between learning success and students’ behavior in the university digital educational environment]. Informatika i obrazovanie = Informatics and Education, 2022, vol. 37, no. 4, pp. 54–63. (In Russ.) URL: Link
Kotova E.E., Pisarev A.S. [The problem of classification of students using the methods of intellectual data analysis]. Izvestiya SPbGETU LETI =LETI Transactions on Electrical Engineering & Computer Science, 2019, no. 4, pp. 32–42. URL: Link (In Russ.)
Bantikova O.I., Tuktamysheva L.M. [Regional demographic processes: Status and prospects]. Azimut nauchnykh issledovanii: ekonomika i upravlenie = Azimuth of Scientific Research: Economics and Administration, 2021, vol. 10, no. 1, pp. 66–71. URL: Link (In Russ.)
