Individual educational trajectory in online learning based on hidden Markov model technologies

Purpose of research . The purpose of this study is to develop and substantiate a methodology for the formation of an individual educational trajectory in online courses by analyzing the educational activity of students and their level of academic achievement. Methods . Hidden Markov models are used in the work, which are well combined with modern machine learning approaches, which enhances their potential in terms of analytics and accurate selection of educational trajectories. The key characteristics of students' learning activity that can be used as observations are highlighted, and a suitable number of hidden states corresponding to different levels of students' academic performance are selected. Results . The scikit-learn library, developed for the Python programming language, was used for experimental model construction. The model was trained on two data arrays: the real sample included 48942 records of students' results in the online course «Internet Resource Development Technologies», and an additional data set contained 18052 records from the Kaggle open repository. The conducted testing confirmed the effectiveness of the proposed methodology, demonstrating an improvement in the quality of education due to an accurate assessment of the student's current state (academic activity, academic achievement), flexible selection of educational materials and other forms of interaction. Conclusion . The obtained results proved the prospects of using the proposed approach, which helps to increase student engagement due to the peculiarities of the perception of educational material, increase the speed of mastering new competencies by optimizing the sequence of presentation of educational material and the possibility of automating the processes of monitoring student progress. The study is of particular interest to specialists working to improve the effectiveness of online learning, and developers of educational platforms who want to integrate such models into their services to support teachers and organizers of the educational process.