Skill-Based Group Allocation of Students for Project-Based Learning Courses Using Genetic Algorithm: Weighted Penalty Model

Abstract

Project-based learning (PBL) is an important component of the practical based assessment of software engineering courses. The success of PBL relies on team composition where all necessary skills to execute the project is needed. Conventionally, facilitators assign the students to the group randomly which results in biased groups where all the necessary skills to complete the project lacks in some of the groups. Most computational tools solve the group assignment problem (GAP) by assigning students to relevant groups based on some general criterion. However, there is a need for a system which allows taking skill preference as a parameter in a limited or unevenly distributed skill set. The system needs to have more or less same strength with the presence of all the skills required to complete the project. In this paper, a method is proposed that uses the canonical genetic algorithm to generate evenly balanced groups by minimizing the intergroup difference. We have employed penalty function to rank the skills and incur a penalty for the non-presence of required skills for proof of concept. Due to unavailability of benchmark datasets, we have used the real data of software engineering courses of our university where good results have been observed.