A Multi-Stage Approach to Personalized Course Selection and Scheduling

Recommender systems that utilize pertinent and available contextual information are applicable to and useful in a broad range of domains. This paper utilizes context-aware recommendation to facilitate personalized education and assist students in selecting courses (or in non-traditional curricula, learning artifacts) that meet curricular requirements, leverage their skills and background, and are relevant to their interests. The research contribution described in this paper is a methodology that generates a schedule of courses (and associated course content) that takes into consideration a student's profile, while meeting curricular and prerequisite requirements and aiming to reduce attributes such as cost and time-to-degree. The optimization problem - multiple integer linear programming problems and a single scheduling problem - is solved in stages using a known linear solver as well as graph-based heuristics. The efficacy of the algorithm is demonstrated through a case study.