Accurate estimation of prefabricated building construction cost based on support vector machine regression

Min Jiang and Boda Li

International Journal of Sustainable Development, 2024, vol. 27, issue 3, 246-261

Abstract: In order to overcome the low accuracy and assembly rate of the traditional construction cost estimation methods for prefabricated building, an accurate estimation method of prefabricated building construction cost based on support vector machine regression is proposed. The cost estimation indicators for prefabricated building construction are selected, and the indicators are preprocessed. The input vector for accurate cost estimation models for prefabricated building construction is determined, including prefabrication cost, assembly cost, direct cost, and indirect cost. A cost estimation model based on support vector machine regression is constructed, and Lagrange transformation is introduced for model training. The trained model is used to obtain accurate cost estimates for prefabricated building construction. The test results show that the cost estimation accuracy of the proposed method is basically maintained at around 99%, and the assembly rate is above 95%, which can ensure the cost estimation accuracy and has strong applicability.

Keywords: support vector machine regression; prefabricated building; construction cost; accurate estimation method; cost estimation model; Lagrange transformation. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=140001 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijsusd:v:27:y:2024:i:3:p:246-261

Access Statistics for this article

More articles in International Journal of Sustainable Development from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().