Construction project cost prediction using text and data mining

T. P. Williams, J. Gong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, text data from a sample of competitively bid California highway projects has been used to predict the likely level of cost overrun in construction projects. A text description of the project and the text of the five largest project line items were used as input. The text data were converted to numerical attributes using text-mining algorithms and singular value decomposition. Classification rules were produced using the Ridor (ripple down rules) classification algorithm. Results of the modeling effort showed that the text data could be used to gain insight into the likely level of project cost overrun.

Original languageEnglish (US)
Title of host publicationProceedings of the 14th International Conference on Civil, Structural and Environmental Engineering Computing, CC 2013
PublisherCivil-Comp Press
Volume102
ISBN (Print)9781905088577
StatePublished - 2013
Event14th International Conference on Civil, Structural and Environmental Engineering Computing, CC 2013 - Cagliari, Sardinia, Italy
Duration: Sep 3 2013Sep 6 2013

Other

Other14th International Conference on Civil, Structural and Environmental Engineering Computing, CC 2013
CountryItaly
CityCagliari, Sardinia
Period9/3/139/6/13

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Civil and Structural Engineering
  • Computational Theory and Mathematics
  • Artificial Intelligence

Keywords

  • Construction costs
  • Data mining
  • Text mining

Fingerprint Dive into the research topics of 'Construction project cost prediction using text and data mining'. Together they form a unique fingerprint.

Cite this