Enhanced Construction Project Duration Estimation Using Artificial Neural Networks: Initial Design and Planning Stages
Maintaining efficiency and quality control during the early phases of construction projects depends on accurate duration estimation. However, because there is not enough data available in the initial stages of project planning, traditional methodologies suffer. To address these challenges, this stu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UTS ePRESS
2025-07-01
|
| Series: | Construction Economics and Building |
| Subjects: | |
| Online Access: | https://epress.lib.uts.edu.au/journals/index.php/AJCEB/article/view/9253 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Maintaining efficiency and quality control during the early phases of construction projects depends on accurate duration estimation. However, because there is not enough data available in the initial stages of project planning, traditional methodologies suffer. To address these challenges, this study presents an innovative approach using artificial neural networks (ANNs) through Python. This method offers reliable predictions for early-stage duration estimation. ANN models were created and validated with 53 design parameters using data from 100 different construction projects in Jordan. Furthermore, the study refined the models to 43 parameters using a questionnaire-driven approach. The average duration estimation accuracy of the ANN models was 90% during the initial stage and 95% during the planning stage, demonstrating their great accuracy. Its uniqueness comes in its application of ANN to early-stage building, an area that has not been extensively studied in the literature to date, and in its demonstration that reliable predictions may be generated in the absence of abundant data. This study demonstrates ANN's effectiveness in enhancing early-stage construction planning by providing stakeholders with a more accurate duration estimation tool than traditional methods. The findings contribute significantly to improving decision-making and project planning in the early phases.
|
|---|---|
| ISSN: | 2204-9029 |