Computational Team Assembly with Fairness Constraints

TL;DR

This paper introduces a two-stage algorithm for team assembly that balances multiple fairness criteria and optimization objectives, addressing complex trade-offs in forming equitable teams.

Contribution

It proposes a novel two-stage multi-objective optimization approach to incorporate fairness constraints into team assembly problems.

Findings

Effective balancing of fairness and skill requirements

Generation of Pareto-optimal team candidates

Improved fairness metrics in assembled teams

Abstract

Team assembly is a problem that demands trade-offs between multiple fairness criteria and computational optimization. We focus on four criteria: (i) fair distribution of workloads within the team, (ii) fair distribution of skills and expertise regarding project requirements, (iii) fair distribution of protected classes in the team, and (iv) fair distribution of the team cost among protected classes. For this problem, we propose a two-stage algorithmic solution. First, a multi-objective optimization procedure is executed and the Pareto candidates that satisfy the project requirements are selected. Second, N random groups are formed containing combinations of these candidates, and a second round of multi-objective optimization is executed, but this time for selecting the groups that optimize the team-assembly criteria.