A near Pareto optimal approach to student–supervisor allocation with two sided preferences and workload balance

• Published in: Applied soft computing Vol. 76; pp. 1 - 15
• Main Authors: Sanchez-Anguix, Victor, Chalumuri, Rithin, Aydoğan, Reyhan, Julian, Vicente
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2019
• Subjects: Artificial intelligence; Genetic algorithms; Matching; Pareto optimal; student–project allocation; Matching; student–project allocation; Pareto optimal; Artificial intelligence; Genetic algorithms
• DOI: 10.1016/j.asoc.2018.11.049
• ISSN: 1568-4946

The problem of allocating students to supervisors for the development of a personal project or a dissertation is a crucial activity in the higher education environment, as it enables students to get feedback on their work from an expert and improve their personal, academic, and professional abilities. In this article, we propose a multi-objective and near Pareto optimal genetic algorithm for the allocation of students to supervisors. The allocation takes into consideration the students and supervisors’ preferences on research/project topics, the lower and upper supervision quotas of supervisors, as well as the workload balance amongst supervisors. We introduce novel mutation and crossover operators for the student–supervisor allocation problem. The experiments carried out show that the components of the genetic algorithm are more apt for the problem than classic components, and that the genetic algorithm is capable of producing allocations that are near Pareto optimal in a reasonable time. •We propose a multiobjective genetic approach for the student–supervisor allocation.•We consider both the students and supervisors’ preferences with regards to project topics.•The algorithm attempts to provide a balanced workload allocation for lecturers.•We introduce novel crossover operators designed for the student–project allocation problem.•The performance of the designed genetic algorithm is close to the optimal solutions and outperforms classic approaches.