A multi-objective formulation for the team formation problem using Krippendorff's disagreement and sociometric cohesion with Pareto-solutions obtained via evolutionary algorithms

Organizations are made up of teams, and team formation is a crucial attribution for decision-makers. Some studies indicate the increased correlation between team arrangement and performance. Moreover, some social aspects of team members' interaction, such as cohesion and diversity have a strong relationship with team performance and innovative practices. In this paper we present a sociometric metric to measure cohesion, and propose the Krippendorff's disagreement metric to compute intra-group diversity by measuring the disagreement among observations. So, a novel bi-objective formulation is presented by maximizing cohesion and disagreement. In order to generate an approximate Pareto front, four multi-objective evolutionary algorithms (MOEA) are tested NSGA-II, U-NSGA-III, SMS-EMOA and SPEA2 have been applied to a benchmark, consisting of a team formation problem with 7 instances with the same structure but different numbers of individuals and groups. On average the four algorithms provided a very close performance generating good Pareto approximations indicating the feasibility for this class of problem.