Abstract: Construction industry enhances the competitiveness of regional economic development of great significance as a pillar industry of national economy. Through the literature review， we established“five factors”evaluation index system of competitive advantage of construction industry and built up an industrial competitiveness model. On the above basis， we used principal component analysis of the“five factors”for feature extraction and reduced the input dimension of BP network importation. According to the nonlinear feature of construction industry competitive advantage system， using a high degree of nonlinear mapping ability of BP neural network， we have efficiently predicted construction industry competitiveness of various provinces in China.