Highway construction investment risk evaluation using BP neural network model

Abstract

Investment risk of highway construction is contained in the whole life cycle from project initiation and design, to construction, to operation and maintenance; therefore investment risk assessment and corresponding precautionary measures are very important to project success. On the basis of China's realities and by Delphi Method this article established an evaluation index system of highway construction project investment risks consists of 19 factors from 6 aspects including political, economic and natural environment, project management, construction technology and operational management. Owing to the non-linear characteristics of the risk factors, the neural network toolbox of MATLAB software was adopted to build a 19 * 12 * 1 BP neural network evaluation model. Finally, this model was applied in investment risk evaluation of JL highway project in Jiangxi province of China; the results show that BP neural network model can be used as a practical effective investment risk evaluation method of highway construction project.