A Novel Approach Based on Support Vector Machine to Forecasting the Construction Project Cost

Abstract

Construction project cost forecasting is a key procedure to the mangement project. An accurate forecast can support the investment decision and ensure the project's feasible at the minimal cost. So reasonable determining and controlling the project cost become the most important task in the budget management of the construction project. A novel regression technique, called Support Vector Machines (SVM), based on the statistical learning theory is exploded in this paper for the prediction of construction project cost. SVM is based on the principle of Structure Risk Minimization as opposed to the principle of Empirical Risk Minimization supported by conventional regression techniques. Through introduced the theory of the SVM-Regression, considered and extracted substances components of construction project as parameters, this paper seted up the Model of the Construction Project Cost Forecasting based on the SVM. The research results show that the prediction accuracy of SVM-Regression is better than that of neural network.