Predicting learning success: research problems and challenges

Abstract

The article is devoted to the problems of learning success prediction. The aim of the work is to discuss current tasks and possible difficulties related to the development of services for predicting learning success in the digital environment of an educational institution. Among the variety of forecasting tasks arising in educational analytics, two main directions were identified and examined in detail: prediction of student dropout and prediction of academic performance for courses of the curriculum. The article discusses examples of creating and using predictive models in the educational process by secondary and higher education organizations. It is noted that despite the large number of studies in this problem field, there are only few examples of successfully implemented regional or at least organizational-level forecasting systems. The authors believe that the main obstacles to building a well-scalable system for supporting learning success based on predictive models are difficulties with data unification, lack of policy of using personal data in learning analytics, lack of feedback mechanisms and activities for correcting learning behavior. Solving each of these problems is a separate serious scientific task. The prospects for using the results of the research are indicated.