Artificial Neural Networks Enhance Construction Project Duration Estimation

Strategic Insights -

Accurate duration estimation is crucial for construction projects to maintain efficiency and quality control during early phases. However, traditional methodologies suffer due to limited data available in initial project planning stages. Researchers at the University of Jordan have proposed an innovative approach using artificial neural networks (ANNs) to address these challenges. This study demonstrates the effectiveness of ANNs in enhancing early-stage construction planning by providing stakeholders with a more accurate duration estimation tool.

Key Takeaways:

  • The research used artificial neural networks (ANNs) through Python to create models for early-stage duration estimation, demonstrating an average accuracy of 90% during the initial stage and 95% during the planning stage.
  • The study refined the models to 43 parameters using a questionnaire-driven approach.
  • The ANNs were created and validated with 53 design parameters using data from 100 different construction projects in Jordan.
  • The study's findings contribute significantly to improving decision-making and project planning in the early phases.
  • The research used a questionnaire-driven approach to refine the models, which resulted in improved accuracy.
  • The study demonstrated the application of ANNs to early-stage building, an area that has not been extensively studied in the literature to date.
  • The ANNs provided reliable predictions even in the absence of abundant data.
  • The study's conclusions suggest that the proposed approach can enhance construction project duration estimation.

Statistics:

  • 90% average duration estimation accuracy of the ANNs during the initial stage.
  • 95% average duration estimation accuracy of the ANNs during the planning stage.
  • 53 design parameters used to validate the ANNs.
  • 100 different construction projects in Jordan used as data for the ANNs.
  • 43 parameters refined using a questionnaire-driven approach.
  • 25(2) Construction Economics and Building journal issue and page number (Construction Economics and Building - http://epress.lib.uts.edu.au/).

Sources:

  • "Enhanced Construction Project Duration Estimation Using Artificial Neural Networks: Initial Design and Planning Stages." Construction Economics and Building, 2025,25(2). (Construction Economics and Building - http://epress.lib.uts.edu.au/journals/index.php/AJCEB).
  • UTS ePRESS.
  • DOI: 10.5130/AJCEB.v25i2.9253.
  • https://doi-org.sdpl.idm.oclc.org/
  • Heba Al-Attar.