Estimating the construction schools cost in Ho Chi Minh City using Artificial Neural Network

Abstract

Construction cost is considered as one of the most important criteria in making decision for investment, especially in the idea formation stage. The paper provides a tool to determine the construction cost of the school during the conceptual design phase, when project information is still sketchy, not detailed yet. This research use artificial neural network techniques for estimating the construction schools cost. The model is based on the weight which set by the excel algorithm and the weight optimization method of the error back propagation. The excel algorithm is tested and optimized by using Statistical Package for the Social Sciences software. The basic model achieves accuracy 90.1% and the optimal model achieves 96.6% accuracy optimization. The optimal weight is used to build the cost estimation model with the automatic calculation program by the excel spreadsheet, which allows for updating the data value limited, updating weight when were adjusted.