Algorithmic construction of individual educational trajectories of students using generative artificial intelligence

Abstract

The digital transformation of higher education is accompanied by an increasing role of personalization of the educational process. The application of intelligent digital technologies creates new opportunities to analyze academic data, formulate recommendations for educational content, and adapt individual educational routes to students’ educational outcomes and professional interests. The aim of the article is to develop an algorithm for personalized student education planning using generative artificial intelligence and to determine the functional capabilities of intelligent digital tools to support adaptive learning in higher education institutions. The methodological basis of the study is the analysis and generalization of scientific sources, the systematization of theoretical provisions on the personalization of education, and a systematic analysis of the educational environment as a holistic structure of interaction among academic data, digital resources, and educational services. The algorithmization method was used to form the stages of an individual educational route based on educational indicators. A comparative analysis of the functional capabilities of modern digital platforms identified tools to support intellectual activities in education. Results. An algorithm for personalizing learning has been developed, comprising successive stages of collecting and structuring academic data, analyzing educational achievements, determining educational priorities, selecting educational content, and adjusting an individual educational route based on results. It has been shown that generative artificial intelligence enables the automated creation of variable educational tasks, the preparation of personalized recommendations, and the selection of educational resources based on applicants’ training levels. Intelligent processing of educational data enables the creation of personalized educational scenarios, the prediction of academic performance, and the prompt updating of educational recommendations. The implementation of the algorithm for personalizing learning increases the efficiency of the educational process, expands the possibilities for analytical support of educational activities, and stimulates students’ engagement in learning. Conclusions. The significant potential of generative artificial intelligence for the development of intelligentized educational services in the higher education system has been established. It has been proven that the algorithmic organization of personalized learning enables flexible adjustment of educational content, more efficient use of educational resources, and expanded possibilities for managing educational activities in the digital environment.