Artificial intelligent support model for multiple criteria decision in construction management

In this study, the factors impacting building projects in Vietnam are discussed. A hybrid model, entitled Slime Mould Algorithm Opposition Tournament Mutation, which integrates Opposition-based learning methods, Tournament Selection and Mutation & Crossover, is used to address these aspects. The hybridization of this model boosts discoverability, promotes convergence, and minimizes local optimization to address the issue of simultaneously optimizing time, cost, quality, and CO2 trade-off problem. The project’s operating procedures are designed to produce the best results possible. Large-scale projects data will be simple to process using the hybrid model, allowing the proposed model to reach its full potential and provide the ideal solution. In addition to evaluating the proposed model, the authors also suggests comparing its results with the benchmarks for other algorithms, including the Slime Mould Algorithm, the multiple-objective Particle Swarm Optimization and the multiple-objective Artificial Bee Colony, in order to confirm its efficacy and achievement. The findings of this study therefore demonstrate that project managers can utilize the developed hybridization model to resolve optimization issues of significant building elements.