Analysis of Industrial Construction activities using Knowledge Discovery Techniques

  • Author / Creator
    Gonzalez, Carlos V.
  • An industrial construction enterprise operating in the City of Edmonton wants to improve its bidding strategies that are currently plagued with uncertainty, lack of information and historical price variability. The present research studies a compilation of documents obtained from company archives detailing previous pipe fabrication performances in order to improve and support decisions during tendering. Two stages constitute the present study: 1) the creation of industrial indicators accumulating company data into a single source facilitating past event consultations; and 2) analysis of data comprising these indicators using a combination of Clustering, Association Rules and Distribution Fitting techniques designed to detect embedded trends and arrangements, enhancing previous performance comprehension. Results obtained in this research ranged from industrial indicator creation to constitution of multiple project profiles, project characterization and statistical distribution fitting reflecting different fabrication aspects and historical knowledge present in previous pipe module fabrication projects.

  • Subjects / Keywords
  • Graduation date
    Fall 2011
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.