Prediction of Students’ Academic Performance: the Correlation between the Results of the Unified State Exam and Academic Success

The purpose of the work is to study the impact of the USE results on the academic performance of university students. We analyzed the data accumulated during the operation of the university information system of a large regional university. We analized data on USE scores and diploma grades received during last 13 years of university education, applying linear regression and cohort analysis to identify correlations between USE scores and student performance in various specialties. The research results demonstrated a significant correlation between USE scores and the average academic performance of students in the university. It is noted that the USE scores should be included as additional explanatory variables when building models for evaluating the educational process. They can also be used to optimize the preparation process of students for university admission and subsequent education. This research is oriented on education professionals involved in assessing and improving the quality of the educational process.

Rochev K.V., Kudelin A.G. (2024). The Analysis of the Correlation between Unified State Exam Results and Students' Academic Achievements. Dataset. https://doi.org/10.48612/MSUPE/65u5-gf9t-45u3

1. Azizova L.R. Edinyy gosudarstvennyy ekzamen (EGE) kak pedagogicheskiy eksperiment: plyusy i minusy [Unified State Exam (USE) as a pedagogical experiment: pros and cons]. Izvestiya Dagestanskogo gosudarstvennogo pedagogicheskogo universiteta. Psikhologo-pedagogicheskie nauki [Bulletin of the Dagestan State Pedagogical University. Psychological and Pedagogical Sciences], 2019, no. 13, 3, pp. 5–9. (In Russ.).
2. Bogdanov E.P., Sukhanov A.V. O prognozirovanii uspevaemosti studentov po rezul'tatam EGE i atributam sotsial'nogo statusa [On predicting student performance based on USE results and social status attributes]. Aktual'nye napravleniya nauchnykh issledovaniy XXI veka: teoriya i praktika [Current Directions of Scientific Research in the 21st Century: Theory and Practice], 2015. Vol. 3, no. 7-3(18-3), pp. 382–386. EDN: TKLXCH, DOI:10.12737/15210 (In Russ.).
3. Vlasova E.A., Mezhennaia N.M., Popov V.S. Sravnitel'nyy analiz rezul'tatov EGE, testa po proverke ostatocnykh znaniy i uspevaemosti pervokursnikov po matematike [Comparative analysis of USE results, residual knowledge test and freshmen’s academic performance in mathematics]. Internet-zhurnal "Mir nauki" [Internet Journal "World of Science"], 2018, no. 5. URL: https://mir-nauki.com/PDF/71PDMN518.pdf (open access). Title from the screen. Lang. Rus., Eng. EDN: YTUYNF. (In Russ.).
4. Erofeeva V.G., Nartova-Bochaver S.K. Chto takoe "Grit" i pochemu ona mozhet byt' lichnostnym resursom? [What is "Grit" and why it may be a personal resource?]. Sovremennaya zarubezhnaya psikhologiya [Modern Foreign Psychology], 2020. Vol. 9, no. 4, pp. 22–31. DOI:10.17759/jmfp.2020090402 (In Russ.).
5. Zamkov O.O., Peresetskiy A.A. EGE i akademicheskie uspehi studentov bakalavriata MIEF NIU VShE [USE and academic achievements of undergraduate students at ICEF HSE]. Prikladnaya ekonometrika [Applied Econometrics], 2013, no. 30(2). EDN: RYGOTT. (In Russ.).
6. Kochetkova T.N., Sashenko A.K. Mnogoaspektnost' problem i vozmozhnostey EGE [The multifaceted nature of problems and opportunities of USE]. Perspektivy nauki [Perspectives of Science], 2020, no. 5, pp. 95–100. (In Russ.).
7. Kudelin A.G., Shakirov D. Informatsionno-analiticheskaya sistema otsenki uchebnogo protsessa FGBOU VO "UGTU" [Information and analytical system for assessing the educational process of USTU]. Informatsionnye tekhnologii v upravlenii i ekonomike [Information Technology in Management and Economics], 2021, no. 2. EDN: RCWUEP. Available at: http://itue.ru/Issue/Article/151 (In Russ.).
8. Min'ko E.V., Min'ko A.E. Kachestvo i vostrebovannost' obrazovatel'nykh uslug [The quality and demand for educational services]. Uchebnoe posobie [Study Guide], Saratov, 2017. (In Russ.).
9. Osipov M.Yu. Mozhet li edinyy gosudarstvennyy ekzamen byt' effektivnym instrumentom otbora abiturientov v vuzy (soderzhatel'nye aspekty)? [Can the Unified State Exam be an effective tool for selecting university applicants (content aspects)?]. Alma Mater (Vestnik vysshey shkoly) [Alma Mater (Bulletin of Higher Education)], 2024, no. 1, pp. 62–68. (In Russ.).
10. Osipov M.Yu. Otsenka effektivnosti EGE kak instrumenta otbora studentov v vuzy (psikhologicheskiy aspekt) [Assessing the effectiveness of USE as a tool for university selection (psychological aspect)]. Vysshee obrazovanie segodnya [Higher Education Today], 2022, no. 9, pp. 90–94. DOI:10.18137/RNU.HET.22.09.P.090 (In Russ.).
11. Pereyaslavskaya L.B., Pereyaslavskiy V.I. Issledovanie korrelyatsiy mezhdu rezul'tatami EGE po matematike abiturientov i ikh uspevaemost'yu v vuze [Study of correlations between USE results in mathematics and university performance of applicants]. Vestnik Assotsiatsii vuzov turizma i servisa [Bulletin of the Association of Universities of Tourism and Services], 2014. Vol. 8, no. 4, pp. 49–56. EDN: SZDJRR, DOI:10.12737/6475 (In Russ.).
12. Poldin O.V. Prognozirovanie uspevaemosti v vuze po rezul'tatam EGE [Predicting university performance based on USE results]. Prikladnaya ekonometrika [Applied Econometrics], 2011, no. 1(21), pp. 56–69. EDN: SLPPNH, DOI:10.32609/0042-8736-2014-9-112-126 (In Russ.).
13. Prakhov I.A. Edinyy gosudarstvennyy ekzamen i determinanty rezul'tativnosti abiturientov: rol' investitsiy v podgotovku k postupleniyu [Unified State Exam and determinants of applicants’ success: the role of investments in preparation for admission]. Prikladnaya ekonometrika [Applied Econometrics], 2012, no. 3(27), pp. 86–108. EDN: PCBQYV. (In Russ.).
14. Prakhov I.A., Yudkevich M.M. Vliyanie dokhoda domokhozyaystv na rezul'taty EGE i vybor vuza [The influence of household income on USE results and university choice]. Voprosy obrazovaniya [Education Issues], 2012, no. 1, pp. 126–147. EDN: OXIMQB, DOI:10.17323/1814-9545-2012-1-126-147 (In Russ.).
15. Rochev K.V., Bazarova A.M. Otsenka faktorov, vliyayushchikh na uspevaemost' studentov na osnove bazy dannykh informatsionnoy sistemy vuza [Evaluation of factors influencing student performance based on the university’s information system database]. Pedagogicheskaya informatika [Pedagogical Informatics], 2022, no. 4, pp. 131–139. EDN: HKYNWR. (In Russ.).
16. Rochev K.V., Kudelin A.G. (2024) Analiz svjazi mezhdu rezul'tatami edinogo gosudarstvennogo jekzamena i akademicheskimi uspehami studentov [The analysis of the relationship between Unified State Exam results and students' academic achievements]. Dataset. DOI:10.48612/MSUPE/65u5-gf9t-45u3
17. Roshchina Ya.M. Povyshaet li EGE dostupnost' vysshego obrazovaniya? [Does the USE increase accessibility to higher education?]. Ekonomika obrazovaniya [Economics of Education], 2006, no. 3(34), pp. 27–50. EDN: HSSASX. (In Russ.).
18. Rusakov S.V., Rusakova O.L., Posokhina K.A. Neyrosetevaya model' prognozirovaniya gruppy riska po uspevaemosti studentov pervogo kursa [Neural network model for predicting the risk group of first-year students' performance]. Sovremennye informatsionnye tekhnologii i IT-obrazovanie [Modern Information Technologies and IT-Education], 2018, no. 14(4), pp. 815–822. EDN: JWGGFH, DOI:10.25559/SITITO.14.201804.815-822 (In Russ.).
19. Semerikov A.V., Glazyrin M.A. Prognozirovanie rezultata uspeshnosti zaversheniya obucheniya potentsial'nym studentom universiteta [Predicting the success of potential students in completing university education]. Informatsionnye tekhnologii v upravlenii i ekonomike [Information Technology in Management and Economics], 2021, no. 4. Available at: http://itue.ru/Issue/Article/181 (In Russ.).
20. Subbotin V.Ya., Khairullina N.G. Pokolenie EGE: posledstviya sovremennogo obrazovaniya dlya budushchego Rossii [The USE generation: the consequences of modern education for the future of Russia]. Vestnik Surgutskogo gosudarstvennogo pedagogicheskogo universiteta [Bulletin of the Surgut State Pedagogical University], 2019, no. 4(61), pp. 155–163. (In Russ.).
21. Timofeeva A.Yu., Avrunev O.E. Otchisleniya studentov v protsesse obucheniya: ob"yasnitel'naya sila EGE [Student dropouts during the learning process: explanatory power of the USE]. In the book: My prodolzhaem traditsii rossiyskoy statistiki. Materialy I Otkrytogo rossiyskogo statisticheskogo kongressa [We Continue the Traditions of Russian Statistics. Materials of the First Open Russian Statistical Congress], 2015, pp. 570–571. (In Russ.).
22. Chernyshova N.A. Svyaz' rezul'tatov EGE i akademicheskikh uspekh studentov v selskokhozyaystvennom vuze [The relationship between USE results and academic success of students in an agricultural university]. Vestnik Nizhegorodskogo universiteta im. N.I. Lobachevskogo. Seriya: Sotsial'nye nauki [Bulletin of N.I. Lobachevsky University of Nizhny Novgorod. Series: Social Sciences], 2017, no. 1(45), pp. 171–177. (In Russ.).
23. Shchapov A.N. Rezul'tat EGE i uspeshnost' obucheniya v vuze [USE results and university academic success]. Khimiya v shkole [Chemistry at School], 2009, no. 6, pp. 43–44. (In Russ.).
24. Alshanqiti A., Namoun A. Predicting student performance and its influential factors using hybrid regression and multi-label classification. IEEE Access, 2020, no. 8, p. 203827-203844. DOI:10.1109/ACCESS.2020.3036572
25. Duckworth A.L. Grit: Why Passion and Persistence are the Secrets to Success. London, 2019. 440 p.
26. Kardaş K., Güvenir A. Analysis of the effects of Quizzes, homeworks and projects on final exam with different machine learning techniques. EMO Journal of Scientific, 2020. Vol. 10(1), pp. 22–29.
27. Musso M.F., Hernández C.F.R., Cascallar E.C. Predicting key educational outcomes in academic trajectories: A machine-learning approach. Higher Education, 2020. Vol. 80(5), pp. 875–894. DOI:10.1007/s10734-020-00520-7
28. Oliveira I.M., Taveira M.D., Porfeli E.J. Career Preparedness and School Achievement of Portuguese Children: Longitudinal Trend Articulations. Frontiers in Psychology, 2017, no. 8. 618 p. DOI:10.3389/fpsyg.2017.00618
29. Opposs D., Baird J.-A., Chankseliani M., Johnson D., Stobart G., Kaushik A., McManus H. Governance structure and standard setting in educational assessment. Assessment in Education, 2020. Vol. 27, no. 2, pp. 192–214. DOI:10.1080/0969594X.2020.1730766
30. Waheed H., Hassan S.U., Aljohani N.R., Hardman J., Alelyani S., Nawaz R. Predicting academic performance of students from VLE big data using deep learning models. Computers in Human Behavior, 2020, no. 104, p. 106189. DOI:10.1016/j.chb.2019.106189
31. Yağcı M. Educational data mining: prediction of students' academic performance using machine learning algorithms. Smart Learning Environments, 2022. Vol. 9, no. 1, pp. 1–19. DOI:10.1186/s40561-022-00192-z