Skip to Main Content
The operating status of a construction project is disclosed periodically in investment risks. As a result, investors usually only get information about the investment risks, an employer may be in after the formal financial statement has been published. If the employer executives intentionally package financial statements with the purpose of hiding the actual status of the constructive project, then investors will have even less chance of obtaining the real financial information. To improve the accuracy of the investment risk prediction, risk ratios, non-risk ratios, and factor analysis had been used to extract adaptable variables. Moreover, the neural network and data mining technique were used to build the investment risk prediction model. The empirical experiment with a total of risk and non-risk ratios and projects as the initial samples obtained a satisfactory result, which testifies for the feasibility and validity of our proposed methods for the investment risks prediction of constructive project.