| Title |
A Study on Predicting Construction Cost of Apartment Housing Projects Based on Support Vector Regression at the Early Project Stage |
| Authors |
Park U-Yeol ; Kim Gwang-Hee |
| Keywords |
Apartment Housing Project ; Preliminary Cost Estimates ; Support Vector Regression ; Accuracy |
| Abstract |
At the early stages where construction costs are estimated under a high level of uncertainty about the project future, accurate estimating becomes crucial to the setting of appropriate project budgets and to control of the construction costs. The purpose of this study was to develop the predicting model of preliminary cost estimates using support vector regression(SVR). Data used in this study are apartment houses' cost constructed from 1997 to 2000 in Seoul. In order to develop the SVR model, the Gaussian radical basis function is used as the Kernel function of SVR, and the parameters(C, ε, γ) is varied to select optimal values for the best prediction performance. The results showed that the SVR model provides a promising alternative for predicting construction cost of apartment housing projects at the early project stage. |