Search results
1 – 1 of 1Heba Al Kailani, Ghaleb J. Sweis, Farouq Sammour, Wasan Omar Maaitah, Rateb J. Sweis and Mohammad Alkailani
The process of predicting construction costs and forecasting price fluctuations is a significant and challenging undertaking for project managers. This study aims to develop a…
Abstract
Purpose
The process of predicting construction costs and forecasting price fluctuations is a significant and challenging undertaking for project managers. This study aims to develop a construction cost index (CCI) for Jordan’s construction industry using fuzzy analytic hierarchy process (FAHP) and predict future CCI values using traditional and machine learning (ML) techniques.
Design/methodology/approach
The most influential cost items were selected by conducting a literature review and confirmatory expert interviews. The cost items’ weights were calculated using FAHP to develop the CCI formula.
Findings
The results showed that the random forest model had the lowest mean absolute percentage error (MAPE) of 1.09%, followed by Extreme Gradient Boosting and K-nearest neighbours with MAPEs of 1.41% and 1.46%, respectively.
Originality/value
The novelty of this study lies within the use of FAHP to address the ambiguity of the impact of various cost items on CCI. The developed CCI equation and ML models are expected to significantly benefit construction managers, investors and policymakers in making informed decisions by enhancing their understanding of cost trends in the construction industry.
Details