Planning Courses for Student Success at the American College of Greece

TL;DR

This paper presents a mathematical programming model for optimizing student course schedules at the American College of Greece, incorporating constraints, multiple objectives, and machine learning to maximize GPA, resulting in efficient, valid schedules.

Contribution

It introduces a novel mixed integer linear programming approach that integrates machine learning for GPA prediction, significantly improving scheduling efficiency and quality over manual methods.

Findings

Schedules generated in under 10 seconds with optimality guarantees.

Automated scheduling reduces advisor time from over an hour to seconds.

Schedules optimize multiple objectives including GPA maximization and course balance.

Abstract

We model the problem of optimizing the schedule of courses a student at the American College of Greece will need to take to complete their studies. We model all constraints set forth by the institution and the department, so that we guarantee the validity of all produced schedules. We formulate several different objectives to optimize in the resulting schedule, including fastest completion time, course difficulty balance, and so on, with a very important objective our model is capable of capturing being the maximization of the expected student GPA given their performance on passed courses using Machine Learning and Data Mining techniques. All resulting problems are Mixed Integer Linear Programming problems with a number of binary variables that is in the order of the maximum number of terms times the number of courses available for the student to take. The resulting Mathematical Programming problem is always solvable by the GUROBI solver in less than 10 seconds on a modern commercial off-the-self PC, whereas the manual process that was installed before used to take department heads that are designated as student advisors more than one hour of their time for every student and was resulting in sub-optimal schedules as measured by the objectives set forth.