байесовские сети,
успеваемость обучающихся,
сложность учебного курса,
вероятностное моделирование,
ранжирование студентов
Abstract
This article proposes an approach to jointly assessing course difficulty and student performance based on Bayesian networks. Unlike traditional methods based solely on GPA or the number of credits, this approach takes into account both objective and subjective factors influencing course difficulty and individual student performance. Using Bayesian methods allows for the integration of prior information (e.g., placement test results or historical course data) and updating assessments based on observed learning outcomes, ensuring transparency and interpretability of findings. This method not only facilitates a more equitable ranking of students based on the difficulty of the courses they complete but also identifies teaching characteristics associated with specific instructors or educational institutions, which can be useful for analyzing the quality of the educational process and its subsequent optimization.
