A New Hybrid Model Based on Least Squares Support Vector Machine for Project Selection Problem in Construction Industry

Effective project selection necessitates considering numerous conflicting factors for the decision making in construction industry. Multiple factors, such as resource requirements, budget control, technological implications and governmental regulations, influence the decision to select an appropriate project selection in construction industry. Among the recent methods and models, an artificial intelligence can be recommended to achieve higher performance than traditional methods in the field. This paper introduces an effective artificial intelligence (AI) model based on modern neural networks to improve the decision making for the projects owners. A hybrid AI model based on least squares support vector machine and cross validation technique is proposed to predict the overall performance of construction projects. The presented model can be successfully utilized for long-term estimation of the performance data in construction industry. Finally, the proposed model is implemented in a real case study for construction projects. To illustrate the capabilities of the proposed model, two well-known AI models, known as back propagation neural network and radial basis function neural network, are taken into consideration. The comparisons demonstrate the superiority of the presented model in terms of its performance and accuracy through the real-world prediction problem.