Forecasting Construction Project Cost Based on BP Neural Network

Cost prediction for the construct project relies on the overall development policy of the project and the development of the related management system based on all related information about the construct project. In this paper, we aim to propose a novel method to accurately forecast construction project cost. Firstly, we propose an index system for construct project cost prediction, which is made up of three parts: 1) Construction cost, 2) Structure cost and 3) Outdoor engineering cost. Secondly, we exploit the BP neural network to forecast construct project cost, and BP neural network exploits error gradient descent algorithm to minimize the mean square errors. Finally, experimental results demonstrate that the proposed algorithm can achieve construct project cost prediction results with high accuracy.