Method for personalization of educational trajectories based on a hierarchical competency model

As education shifts into the digital environment, the gap between what graduates actually know and what the labor market expects from them keeps widening. According to estimates by the World Economic Forum, about 39% of core skills will need to be updated by 2030, which makes the timely identification of competency gaps among students particularly important. Most existing approaches to the personalization of learning pathways operate at the level of individual disciplines and do not offer a systematic comparison between the competencies a student has already acquired and those required by a particular professional role, especially when the hierarchical relations between skills are taken into account. The present study develops a method that brings together heterogeneous data from a student’s digital profile and produces recommendations aligned with a selected target role. The proposed approach combines: a hierarchical competency model with a three-level proficiency scale (basic, intermediate, advanced); an aggregation mechanism that merges information from several sources while damping outdated records by an exponential rule; a multi-level gap analysis that provides a quantitative estimate of the deficit relative to role requirements; and (iv) a hybrid recommendation algorithm in which content-based and collaborative filtering are combined with a level-compatibility function. The method was tested on a synthetic dataset consisting of 100 student profiles, 25 competencies, 60 educational activities and 5 professional IT roles. The results confirm the viability of the approach: coverage of deficient competencies (Coverage@5) reaches 0.81, the estimated reduction in the aggregate gap is 46 %, and the average readiness index rises from 51 % to 76 %. The comparison with baseline strategies shows a statistically significant advantage of the proposed method (p < 0.001). Moving from a binary to a three-level proficiency scale increases Coverage by 12 percentage points.

1. Arkhipova Z.V., Sorokin A.V. Analysis of approaches to the development of recommendation systems in the field of education. System analysis & Mathematical modeling. 2024;6(2):133–145. (In Russ.). https://doi.org/10.17150/2713-1734.2024.6(2).133-145

2. Kachurin N.S. The concept of the method of personalizing the trajectory of professional development of students in the educational environment of the university. Volgograd State Technical University. 2024;136–137. (In Russ.).

3. Chastikova V.A., Pseush A.G. Application of swarm intelligence algorithms in the process of building individual educational trajectories. Bulletin of the Adyghe State University. 2022;2(301). (In Russ.). https://doi.org/10.53598/2410-3225-2022-2-301-84-90

4. Loginova E.G., Denisov N.L. Using Process Mining algorithms to identify patterns of student behavior. Vestnik of Astrakhan State Technical University. Series: Management, Computer Science and Informatics. 2024;(3):75–84. (In Russ.). https://doi.org/10.24143/2072-9502-2024-3-75-84

5. Pustovalova N.V. Ontological model of interaction between educational content and learner in intelligent tutorial system architecture. Vestnik of Astrakhan State Technical University. Series: Management, Computer Science and Informatics. 2021;(4):113–125. (In Russ.). https://doi.org/10.24143/2072-9502-2021-4-113-125

6. Podkolzin M.M. Intelligent adaptive learning system based on neural networks for personalization of educational trajectories of Russian university students. Informatics and Education. 2024;39(6):65–81. (In Russ.). https://doi.org/10.32517/0234-0453-2024-39-6-65-81

7. Klishin A.P., Vlasov D.V., Lyskov A.A. Decision Support in the Educational Process of the University based on a Cognitive Learning Model using a Neural Network. Vestnik NSU. Series: Information Technologies. 2024;22(4):33–48. (In Russ.). https://doi.org/10.25205/1818-7900-2024-22-4-33-48

8. Zakieva R.R. Model of educational quality management based on continuous objective assessment of professional development of a technical university student. Modern High Technologies. 2023;(2):144–148. (In Russ.).

9. Khudzhina M.V., Karakozov S.D. Ensuring Competitive Advantages of University Graduates in the Regional Labor Market: A Didactic Model (On the Example of Training IT Graduates). Prepodavatel XXI vek. 2023;(3):20–33. (In Russ.). https://doi.org/10.31862/2073-9613-2023-3-20-33

10. Kachurin N.S. Research and analysis of problems in the field of accounting for students' scientific and educational achievements. In: Volzhsky – Territory of Development: Proceedings of the XXIX Interuniversity Scientific and Practical Conference of Students and Young Scientists Dedicated to the 70th Anniversary of the City of Volzhsky, 13–23 May 2024, Volzhsky, Russia. Volgograd: Volgograd State Technical University; 2024. P. 36. (In Russ.).