Cost assessment of construction projects through neural networks

Abstract

Construction performance parameters have experienced greater international attention and discussion in recentyears. In this study, the change in the load-bearing system cost of a reinforced concrete housing estate building was investigatedin relation to the building importance factor, earthquake region, soil type, floor area, and the number of stories. Three different housing estate projects with seven and fifteen stories were investigated. The structural design calculations were performed according to four different soil types, four different earthquake regions, and four different importance factors. With regards toeach combination, project costs were calculated. The changes in the cost were examined with artificial neural network and multiple regression models. According to the results of the analysis, the building importance factor was the most significant component, while earthquake region was the second most significant, followed by the factors of the number of floors and the soil type. Key words: cost estimation, artificial neural network, earthquake region, building importance factor, soil type, housing estate project.