Incorporating Machine Learning to Evaluate Solutions to the University Course Timetabling Problem

Abstract

Evaluating solutions to optimization problems is arguably the most important step for heuristic algorithms, as it is used to guide the algorithms towards the optimal solution in the solution search space. Research has shown evaluation functions to some optimization problems to be impractical to compute and have thus found surrogate less expensive evaluation functions to those problems. This study investigates the extent to which supervised learning algorithms can be used to find approximations to evaluation functions for the university course timetabling problem. Up to 97 percent of the time, the traditional evaluation function agreed with the supervised learning regression model on the result of comparison of the quality of pair of solutions to the university course timetabling problem, suggesting that supervised learning regression models can be suitable alternatives for optimization problems' evaluation functions.