Research on Forecasting the Cost of Residential Construction Based on PCA and LS-SVM

DOI

10.2991/emcm-15.2016.17How to use a DOI?

Keywords

Residential construction; Indicators; costs forecasting; Principal component analysis; Least squares support vector machine

Abstract

To forecast the costs of a residential construction rapidly and accurately in the initial stage of construction and lack of relevant information. Based on the strengths and weaknesses of previous studies about it, a new model to forecast the costs of a residential construction which is based on Principal Component Analysis (PCA) and Least Squares Support Vector Machine (LS-SVM) is proposed. First based on the factors analysis in the costs of a residential construction, chooses the indicators and samples of residential construction for the prediction of the Construction Costs, after which submits the selected indicators data to the Principal Component Analysis(PCA) to eliminate the Correlation in it; then, the new indicators data is imported into the Least Squares Support Vector Machine (LS-SVM) and training in it to build a new model to forecast the costs of a residential construction. Finally, selects 5 projects in conjunction with the new model for simulation analysis, the relative error are controlled within±7%.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhongfu Qin
AU  - Xiaolong Lei
AU  - Liqing Meng
PY  - 2016/02
DA  - 2016/02
TI  - Research on Forecasting the Cost of Residential Construction Based on PCA and LS-SVM
BT  - Proceedings of the International Conference on Electronics, Mechanics, Culture and Medicine
PB  - Atlantis Press
SP  - 84
EP  - 88
SN  - 2352-538X
UR  - https://doi.org/10.2991/emcm-15.2016.17
DO  - 10.2991/emcm-15.2016.17
ID  - Qin2016/02
ER  -