Science for Education Today, 2019, vol. 9, no. 6, pp. 73–87

Prediction of student performance in blended learning utilizing learning analytics data

Ozerova G. P. 1 (Vladivostok, Russian Federation), Pavlenko G. F. 1 (Vladivostok, Russian Federation)
1 Far Eastern Federal University

Introduction. This paper is devoted to predicting performance of students involved in blended learning. The objective of the research is to identify characteristics of predicting student performance in blended learning using learning analytics data.
Materials and Methods. Primary methods used in the research are the following: theoretical analysis and generalization of previous studies, theoretical and practical methods of educational research, statistical processing of empirical data, machine learning and random events modelling.
Results. The research has found that predication has to be based on the criteria which determine learning success. Metrics for the criteria can be obtained through learning analytics data. Students should be split into groups according to their academic performance every time they complete their assignments in order to identify low performers who require support from academic staff. In order to predict future performance more efficiently, we need to accumulate dynamics of how students get re-classified into groups using discrete Markov Chains.
Conclusions. Prediction of student performance based on learning analytics data allows to identify students who fall into high risk group, predict how students can be distributed among performance groups, and adopt teaching materials to student needs.


Learning success; Blended learning; Learning management system; Learning analytics; Prediction; Classification; Discrete Markov Chains

Prominence Percentile SciVal: 99.464 Online Courses | Learner Behaviour | Blended Learning

Prediction of student performance in blended learning utilizing learning analytics data

For citation:
Ozerova G. P., Pavlenko G. F. Prediction of student performance in blended learning utilizing learning analytics data. Science for Education Today, 2019, vol. 9, no. 6, pp. 73–87. DOI:
  1. Boelens R., De Wever B., Voet M. Four key challenges to the design of blended learning: A systematic literature review. Educational Research Review, 2017, vol. 22, pp. 1–18. DOI:
  2. Jones K. M. Learning analytics and higher education: a proposed model for establishing informed consent mechanisms to promote student privacy and autonomy. International Journal of Educational Technology in Higher Education, 2019, vol. 16, article number 24. DOI:
  3. Schumacher C., Ifenthaler D. Features students really expect from learning analytics. Computers in Human Behavior, 2018, vol. 78, pp. 397–407. DOI:
  4. Nistor N., Hernández-Garcíacc Á. What types of data are used in learning analytics? An overview of six cases. Computers in Human Behavior, 2018, vol. 89, pp. 335–338. DOI:
  5. Bystrova T. Yu., Larionova V. A., Sinitsyn E. V., Tolmachev A. V. Learning analytics in massive open online courses as a tool for predicting learner performance. Voprosy obrazovaniya / Educational Studies Moscow, 2018, no. 4, pp. 139–166. DOI: URL:
  6. Patarakin E. D. Learning analytic to facilitate group network collaboration. Vysshee Оbrazovanie v Rossii (Higher Education in Russia), 2015, no. 5, pp. 145–154. (in Russian) URL:
  7. Lim L. A., Gentili S., Pardo A., Kovanović V., Whitelock-Wainwright A., Gašević D., Dawson S. What changes, and for whom? A study of the impact of learning analytics-based process feedback in a large course. Learning and Instruction, 2019. DOI:
  8. Birina O. V. The concept of successful learning in modern pedagogical and psychological theories. Fundamental Research, 2014, no. 8-2, pp. 438–443. (in Russian) URL:
  9. Gardner J., Brooks C. Student success prediction in MOOCs. User Modeling and User-Adapted Interaction, 2018, vol. 28, issue 2, pp. 127–203. DOI:
  10. Raga R. Raga J. Early prediction of student performance in blended learning courses using deep neural networks International. Symposium on Educational Technology, 2019, pp. 39–43. DOI:
  11. Xu X., Wang J., Peng H., Wu R. Prediction of academic performance associated with internet usage behaviors using machine learning algorithms. Computers in Human Behavior, 2019, vol. 98, pp.  166–173. DOI:
  12. Moreno-Marcos P. M., Alario-Hoyos C., Muñoz-Merino P. J., Kloos C. D. Prediction in MOOCs: A review and future research directions. Transactions on Learning Technologies, 2019, vol. 12, issue 3, pp. 384–401. DOI:
  13. Ellis R. A., Pardo A., Han F. Quality in blended learning environments–Significant differences in how students approach learning collaborations. Computers and Education, 2016, vol. 102, pp. 90–102. DOI:
  14. Conijn R., Van den Beemt A., Cuijpers P. Predicting student performance in a blended MOOC.  Journal of Computer Assisted Learning, 2018, vol. 34, issue 5, pp. 615–628. DOI:
  15. Kim D., Yoon M., Jo I. H., Branch R. M. Learning analytics to support self-regulated learning in asynchronous online courses: A case study at a women’s university in South Korea. Computers and Education, 2018, vol. 127, pp. 233–255. DOI:
  16. Conijn R., Snijders C., Kleingeld A., Matzat U. Predicting student performance from LMS data: A comparison of 17 blended courses using Moodle. Transactions on Learning Technologies, 2017, vol. 10, issue 1, pp. 17–29. DOI:
  17. Fei M., Yeung D. Temporal models for predicting student dropout in massive open online courses. International Conference on Data Mining Workshop, 2015, pp. 256–263. DOI:
  18. Macina J., Srba I., Williams J. J, Bielikova M. Educational question routing in online student communities. ACM Conference on Recommender Systems, 2017, pp. 47–55. DOI:
  19. Topîrceanua A., Grosseckb G. Decision tree learning used for the classification of student archetypes in online courses. Procedia Computer Science, 2017, vol. 112, pp. 51–60. DOI:
  20. Xing W., Chen X., Stein J., Marcinkowski M. Temporal predication of dropouts in MOOCs: Reaching the low hanging fruit through stacking generalization. Computers in Human Behavior, 2016, vol. 58, pp. 119–129. DOI:
  21. Laveti R. N., Kuppili S., Ch J., Pal S. N., Babu N. S. C. Implementation of learning analytics framework for MOOCs using state-of-the-art in-memory computing. National Conference on E-Learning and E-Learning Technologies, 2017, pp. 1–6. DOI:
  22. Gamulin J., Gamulin O., Kermek D. Using fourier coefficients in time series analysis for student performance prediction in blended learning environments. Expert Systems, 2016, vol. 32, issue 2, pp. 189–200. DOI:
  23. Nam S., Frishkoff G., Collins-Thompson K. Predicting Students disengaged behaviors in an online meaning-generation task. IEEE Transactions on Learning Technologies, 2018, vol. 11, issue 3, pp.  362–375. DOI:
  24. Arabshahi F., Huang F., Anandkumar A., Butts C. T., Fitzhugh S. M. Are you going to the party: Depends, who else is coming? [Learning hidden group dynamics via conditional latent tree models]. International Conference on Data Mining, 2015, pp. 697–702. DOI:
  25. Youssef M., Mohammed S., Hamada E. K., Wafaa B. F. A predictive approach based on efficient feature selection and learning algorithms’ competition: Case of learners’ dropout in MOOCs. Education and Information Technologies, 2019, vol. 24, issue 6, pp. 3591–3618. DOI:
  26. Shestakova L. G., Richter T. V. Student’s readiness for self-organization: Indicators of evaluation and self-evaluation. Science for Education Today, 2019, vol. 9, issue 3, pp. 138–150. DOI: URL:
  27. Klein C., Lester J., Rangwala H., Johri A. Learning analytics tools in higher education: Adoption at the intersection of institutional commitment and individual action. Review of Higher Education, 2019, vol. 42, issue 2, pp. 565–593. DOI:
Date of the publication 31.12.2019