Reputation aware optimal team formation for collaborative software crowdsourcing in industry 5.0

Collaborative software crowdsourcing (CSC) is now a vital part of the technological workforce due to the rising need for software solutions in an industry 5.0 smart city that exceeds performance standards without sacrificing cost-effectiveness. When a buyer intends to hire a group of productive workers within their budget limit and time frame, the CSC offers a potential solution for executing a software module in crowdsourcing. Existing literature works are limited by team-building mechanisms in CSC without considering reputation and technical competency, which are crucial to building an effective team. In this paper, we have developed an AI-based meta-heuristic particle swarm optimization (PSO) algorithm, which gives personalized solutions for intelligent CSC team-building problems, namely PCS system, that effectively forms worker-teams. We furthermore develop a reputation-based scheme by considering workers’ competency and prior performance to enhance the dependability and trustworthiness of the workers in the CSC platform by employing an exponentially weighted moving average (EWMA) and the multi-step time balancing weight-based method. The developed PCS system also offers a utility function to buyers weighing the cost against task quality. All experiments are carried out in MATLAB and the results have shown that the developed PCS system enhances the buyer’s quality-of-experience (QoE) and utility as high as 30% and 25%, respectively compared to the state-of-the-art works.