MODELS OF INDIVIDUALIZED LEARNING BASED ON DECISION-MAKING THEORY: ANALYSIS OF APPROACHES TO THE DEVELOPMENT OF THEIR

Abstract

With the increasing availability of data and the development of IT, especially machine learning, it is possible to acquire personalized educational experiences that will apply to the needs and abilities of each student. Decision theory provides a framework for making optimal decisions about what content, when, and how to deliver to each student. The variety of IT capabilities is quite broad. Therefore, along with the fact that decision-making models can significantly improve the effectiveness of individualized learning by providing a more accurate and adaptive approach to the needs of each student, it is advisable to analyze existing solutions for their development. The purpose of the article is to explore strategies for the development of individualized learning models based on decision theory. Several critical aspects related to models of individualized learning in the context of decision theory are identified and briefly described: (1) the theory of subjective expected utility; (2) dynamic decision-making processes; (3) evaluation and updating of expectations; (4) information value of experiments The analysis did not reveal the existence of models of individualized learning based on decision theory, but we found that the use of such theories as bounded rationality, prospect theory, multi-criteria decision making, and the theory of decision making can be used to meet the needs of students. In particular, we can talk about the efficient use of resources, helping to overcome inequality in learning, and reducing the costs associated with traditional teaching methods. Individualized learning models can reduce the costs associated with traditional teaching methods, such as one-size-fits-all curricula and overcrowded classrooms, etc.