Tracking Performance and Forming Study Groups for Prep Courses Using Probabilistic Graphical Models: (Extended Abstract)

Yoram Bachrach, Yoad Lewenberg, Jeffrey S. Rosenschein, Yair Zick

Abstract: Efficient tracking of class performance across topics is an important aspect of classroom teaching; this is especially true for psychometric general intelligence exams, which test a varied range of abilities. We develop a framework that uncovers a hidden thematic structure underlying student responses to a large pool of questions, using a probabilistic graphical model.