Personalized Course Selection Optimization Using an Ising Machine

Many students spend a lot of time and effort manually selecting courses, due to the large number of candidate courses offered by universities. We regard course selection as a combinatorial optimization problem and define it as an NP-hard problem. In this paper, we propose a QUBO (Quadratic Unconstrained Binary Optimization) formulation for solving the course selection problem, and solve the problem with an Ising machine. Experimental evaluations demonstrate that for the instance with the largest number of courses, our approach solves a personalized course selection problem 20X times faster than the conventional simulated annealing.