Multi-objective intelligent model for optimizing labor allocation in construction projects

Purpose Typically, the number of workers per team is determined based on experience. This study aims to propose an integrated intelligent model aimed at reducing lost productivity and optimizing team sizes in construction projects to align with stakeholder interests and project objectives. The model focuses on maximizing profit and minimizing loss under the current project conditions and available resources. Subsequently, the model provides reliable estimates of the necessary information and the impacts of worker arrangement selection on team performance for clearer decision-making by managers. Design/methodology/approach This study extracts stakeholder criteria weights using the best-worst method. The outputs are integrated with TOPSIS calculations to determine the optimal number of workers per group based on productivity and project needs. Furthermore, a hybrid metaheuristic algorithm combined with artificial neural networks is optimized to accurately estimate the impact of managerial decisions. Findings A case study was conducted using data from a construction project. Results significantly demonstrated the impact of project goal orientation and stakeholder criteria on prioritizing workforce sizes for achieving maximum productivity. The intelligent model adapts to changing project conditions. In addition, an optimal combination of candidate metaheuristics with neural networks was achieved for accurately estimating the impacts of worker arrangements. Practical implications This dynamic multi-objective model facilitates optimal productivity aligned with stakeholder goals and current project conditions, providing informed insights for managers. Originality/value This model presents an intelligent, knowledge-based approach addressing the unique and dynamic environments of projects to enhance workforce productivity while offering reliable forecasts applicable across diverse construction activities.