A Model for Forecasting Owner’s Project Management Resources

  • Author / Creator
    Elkholosy, Hady
  • This research involves the development of a forecasting model that will aid project managers in estimating the owner’s project management staff requirements for a construction project utilizing historical data. This will support project managers in the decisions of hiring new resources or working with the current available ones as well. The objective of this research is to provide a methodology that will help in forecasting the project management staff hours for a given project by studying the factors that impact staff requirements and developing an analytical model utilizing data mining techniques. The research includes understanding industry practices in resource allocation and estimation, collecting and analyzing historical data, and evaluating different machine learning algorithms, such as artificial neural networks, multiple linear regression, KNN and random forests, to forecast project management hours.
    The contributions of this research are combining industry practices and literature review to identify the projects’ features that affect the staffing requirements, proposing a data acquisition model that will help industry practitioners in collecting these attributes properly, and developing a neural network model to utilize the data collected and forecast the owner’s project management hours required for buildings, infrastructure and industrial projects.

  • Subjects / Keywords
  • Graduation date
    Fall 2020
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.