No abstract

No abstract

No abstract

No abstract

Purpose Construction materials comprise a major part of the total construction cost. Given the importance of bitumen as a fundamental material in construction projects, it is imperative to have an accurate forecast of its consumption in the planning and material sourcing phases on the project. This study aims to introduce a flexible genetic algorithm-fuzzy regression approach for forecasting the future bitumen consumption. Design/methodology/approach In the proposed approach, the parameter tuning process is performed on all parameters of genetic algorithm (GA), and the finest coefficients with minimum errors are identified. Moreover, the fuzzy regression (FR) model is used for estimation. Analysis of variance (ANOVA) is used for selecting among GA, FR or conventional regression (CR). To show the applicability of the proposed approach, Iran’s bitumen consumption data in the period of 1991-2006 are used as a case study. Findings Production, import, export, road construction and price are considered as the input data used in the present study. It was concluded that, among all the forecasting methods used in this study, GA was the best method for estimating. Practical implications The proposed approach outperforms the conventional forecasting methods for the case of bitumen which is a fundamental economic ingredient in road construction projects. This approach is flexible, in terms of amount and uncertainty of the input data, and can be easily adapted for forecasting other materials and in different construction projects. It can have important implications for the managers and policy makers in the construction market where accurate estimation of the raw material demand is crucial. Originality/value This is the first in this field introducing a flexible GA-FR approach for improving bitumen consumption estimation in the construction literature. The proposed approach’s significance has two folds. Firstly, it is completely flexible. Secondly, it uses CRs as an alternative approach for estimation because of its dynamic structure.