Prioritizing Labour Productivity Improvement Strategies by Integrating Hybrid Feature Selection, Fuzzy Multi-Criteria Decision-Making, and Fuzzy Cognitive Maps

  • Author / Creator
    Kazerooni, Mohammad Matin
  • Construction labour productivity (CLP), as a key performance index in the construction sector, is affected by various factors such as crew motivation and working conditions that are highly interconnected and vary on a project-by-project basis. CLP can be enhanced by properly practicing appropriate improvement strategies in terms of cost, duration, feasibility, and adaptability. Understanding factors that affect labour productivity is important for making strategic decisions and selecting appropriate CLP improvement strategies. However, identification of most-value-adding CLP factors is a challenging task, because CLP is situated in a high-dimensional feature space where a number interconnected quantitative factors (e.g., temperature) and qualitative factors (e.g., team spirit of crew) affect CLP directly or indirectly. Therefore, a research gap exists regarding methods for identifying the key factors affecting CLP by considering the dynamics, interconnection, and combined impact of the factors without dependency on expert knowledge. Another challenging task in the process of selecting improvement strategies is that budget, time, and resource restrictions force companies to implement only a limited number of CLP improvement strategies. Therefore, research gaps exist with respect to a model’s ability to support selection and implementation of optimal CLP improvement strategies for a given project by quantifying the effect of strategies on CLP while simultaneously considering causal relationship among factors affecting CLP and project characteristics.
    To bridge the existing gaps, this thesis aims at proposing a novel framework for prioritizing CLP improvement strategies by combining two models. First, a hybrid feature selection model is proposed to identify the most value-adding CLP factors for a given project based on the interconnection of CLP factors without dependency on expert knowledge. Second, a decision-support model is proposed for integrating fuzzy multi-criteria decision-making and fuzzy cognitive maps in order to rank CLP improvement strategies based on their impact on CLP, causal relationships among CLP factors, and project characteristics. The top three factors most influential on CLP include: (1) fairness of work assignment, (2) complexity of task, and (3) repetitiveness of task. The top three most effective CLP improvement strategies for concrete-pouring activities in building projects include: (1) providing clear instructions to craftspeople on how to complete tasks before their execution, (2) training labourers to achieve the latest concrete-pouring techniques, and (3) applying preventive maintenance to heating and air-conditioning systems to make sure they are in working order. The contribution of this study is to provide a systematic approach for identifying the most-value adding CLP factors and analyzing and selecting practical CLP improvement strategies by modeling the relationships among the key factors affecting CLP and quantifying the effect of various strategies on CLP. The findings of this study are expected to support construction practitioners in identifying influential CLP factors and effective improvement strategies to enhance the level of CLP in construction projects.

  • Subjects / Keywords
  • Graduation date
    Fall 2021
  • 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.