PERSONALIZED EDUCATIONAL TRAJECTORY: A MULTI-LEVEL ARCHITECTURE OF PREDICTIVE ANALYTICS OF STUDENTS’ COGNITIVE CHARACTERISTICS
Back to articles of current journal| PDF: |  |
Author(s): | Maslova Yu. V., R. Z. Bogoudinova, |
| Number of journal: | 3(76) | Date: | September 2026 |
| Annotation: | The increasing pace of widespread digital transformation, including in the field of education, is reflexively less able to take into account the dynamically increasing variety of cognitive styles, stable individual ways of learning material, motivation of students, etc. The advantage of a personalized educational trajectory makes it possible to take into account different variations in the set of characteristics, knowledge, potential of students and adapt the pace and level of educational material to individual abilities The article presents the author’s model of a personalized educational trajectory with a logically constructed multilevel architecture of predictive analytics, consisting of six interconnected modules. Machine learning methods, including clustering and regression analysis, allow students to predict the success of mastering the material based on personal data and automatically adjust the sequence of training modules. And the algorithms of recommendation systems can select additional exercises for students experiencing difficulties, or accelerate the pace for advanced students. The federal state educational standards of the new generation explicitly prescribe the possibility of building individual curricula using electronic resources. The study contains an experimental verification of the model on the bases of educational organizations of various fields. The scientific novelty of the research consists in overcoming the fragmentation of algorithmic solutions typical of existing developments by integrating them into a single technological circuit, as well as in obtaining comparable empirical data on the effectiveness of the model. The risks of scaling predictive analytics in educational practice and promising areas for further development of the topic are outlined. In conclusion, the results obtained are presented, on the basis of which it is concluded that the implementation of a personalized educational trajectory and predictive analytics is effective; in particular, it is stated that the development and implementation of a model based on a set of six proposed modules provides a synergetic effect, i.e. the ability to maximize the student’s work with educational material and the degree of its assimilation. As a result, it allows for a statistically significant increase in academic performance, the formation of professional competencies and academic motivation of students, and the construction of an individual learning trajectory. | ||
| Keywords: | personalized educational trajectory, predictive analytics, students’ cognitive characteristics, student clustering, educational content classification, recommendation systems, adaptive learning, digital educational environment, competency- based approach, higher education |
||
| For citation: | Bogoudinova R. Z., Maslova Yu. V. Personalized educational trajectory: a multi-level architecture of predictive analytics of students’ cognitive characteristics. Biznes. Obrazovanie. Pravo = Business. Education. Law. 2026;3(76):232—237. DOI: 10.25683/VOLBI.2026.76.1712. |
||