ИНТЕЛИГЕНТНА АГЕНТНО-БАЗИРАНА СИСТЕМА ЗА ПОДПОМАГАНЕ НА МЕХАНИЗМА ЗА ОБХВАТ И ЗАДЪРЖАНЕ НА УЧЕНИЦИ В ОБРАЗОВАТЕЛНАТА СИСТЕМА В БЪЛГАРИЯ: МЕТОДИЧЕСКИ МОДЕЛ ЗА ПРИЛОЖЕНИЕ В УЧИЛИЩЕ

Боян Любомиров Беличев, Венета Веселинова Табакова-Комсалова, Станимир Недялков Стоянов
Пловдивски университет „Паисий Хилендарски“, Пловдив

AN INTELLIGENT AGENT-BASED SYSTEM TO SUPPORT THE MECHANISM FOR RECRUITING AND RETAINING STUDENTS IN THE EDUCATION SYSTEM IN BULGARIA: A METHODOLOGICAL MODEL FOR SCHOOL IMPLEMENTATION

Boyan Lyubomirov Belichev, Veneta Veselinova Tabakova-Komsalova, Stanimir Nedyalkov Stoyanov
University of Plovdiv “Paisii Hilendarski”, Plovdiv, Bulgaria

Abstract: The article presents an implemented intelligent agent-based prototype as a methodological tool for supporting the mechanism for recruiting and retaining students in the Bulgarian education system. The original contribution is a school-oriented model that integrates attendance, achievement, participation, family communication, socio-economic, health and intervention data into a unified pedagogical profile. The system is realised through a Streamlit interface, an MCP coordination layer, specialised agents, relational and vector storage, semantic search and retrieval-augmented generation for contextual analysis and intervention planning. The empirical part is interpreted as a pilot simulation in a school context with depersonalised real data, in which personal identifiers are replaced in accordance with GDPR requirements. The proposed approach is not an autonomous decision-making mechanism, but an assistant to teachers, class tutors, school psychologists and management teams. Its methodological value lies in early identification of students at risk, explanation of the factors that form the risk profile, generation of coordinated measures and periodic evaluation of their effect. Ethical limitations related to data quality, privacy, bias and possible labelling are discussed as necessary conditions for responsible implementation.

Keywords: agent-based system, dropout prevention, student retention, educational data mining, school support

References:

1. Tinto, V. Dropout from higher education: A theoretical synthesis of recent research. Review of Educational Research, 45(1), 89–125, 1975.
2. Dekker, G., Pechenizkiy, M., & Vleeshouwers, J. Predicting students drop out: A case study. In Proceedings of the 2nd International Conference on Educational Data Mining, 2009
3. Kotsiantis, S., Pierrakeas, C., & Pintelas, P. Predicting students’ performance in distance learning using machine learning techniques. Applied Artificial Intelligence, 18(5), 411–426, 2010.
4. Lykourentzou, I., Giannoukos, I., Nikolopoulos, V., Mpardis, G., & Loumos, V. Dropout prediction in e-learning courses through the combination of machine learning techniques. Computers & Education, 53(3), 950–965, 2009.
5. Romero, C., S. Ventura, Educational data mining and learning analytics: An updated survey, 2020.
6. Baker, R. S., P. S. Inventado, Educational data mining and learning analytics. In J. A. Larusson & B. White (Eds.), Learning Analytics: From Research to Practice. Springer, 2014.
7. Mduma, N., Kalegele, K., & Machuve, D. A survey of machine learning approaches and techniques for student dropout prediction. Data Science Journal, 18(1), 2019
8. Colpo, M., et al. Educational Data Mining for Dropout Prediction: Trends, Opportunities, and Challenges. Revista Brasileira de Informática na Educação, 2024
9. Márquez-Vera, C., Cano, A., Romero, C., & Ventura, S. Early dropout prediction using data mining: A case study with high school students. Expert Systems, 33(1), 107–124, 2016.
10. Dasi, H., & Kanakala, S. Student dropout prediction using machine learning techniques. International Journal of Intelligent Systems and Applications in Engineering, 2022

READ FULL PAPER