A Neural Network Model for Construction Projects Site Overhead Cost Estimating in Egypt

TL;DR

This paper develops an ANN-based model to accurately estimate site overhead costs for construction projects in Egypt, improving cost management and project planning.

Contribution

It introduces a neural network approach specifically tailored for Egyptian construction project overhead cost estimation, using real-life data from 2002-2009.

Findings

Neural network model achieved high accuracy in cost estimation.

The model effectively predicts overhead costs as a percentage of total project price.

Application of ANN improves estimation reliability over manual methods.

Abstract

Estimating of the overhead costs of building construction projects is an important task in the management of these projects. The quality of construction management depends heavily on their accurate cost estimation. Construction costs prediction is a very difficult and sophisticated task especially when using manual calculation methods. This paper uses Artificial Neural Network (ANN) approach to develop a parametric cost-estimating model for site overhead cost in Egypt. Fifty-two actual real-life cases of building projects constructed in Egypt during the seven year period 2002-2009 were used as training materials. The neural network architecture is presented for the estimation of the site overhead costs as a percentage from the total project price.