Cost Estimation for Building Construction Projects in Gaza Strip Using Artificial Neural Network (ANN)

Abstract

Early stage cost estimate plays a significant role in the success of any construction project. All parties involved in the construction of a project; owners, contractors, and donors are in need of reliable information about the cost in the early stages of the project, where very limited drawings and details are available during this stage. This research aims at developing a model to estimate the cost of building construction projects with a high degree of accuracy and without the need for detailed information or drawings by using Artificial Neural Network (ANN). ANN is new approach that is used in cost estimation, which is able to learn from experience and examples and deal with non-linear problems. It can perform tasks involving incomplete data sets, fuzzy or incomplete information and for highly complex problems. In order to build this model, quantitative and qualitative techniques were utilized to identify the significant parameters for the building project costs including skeleton and finishing phases. A database of 169 building projects was collected from the construction industry in Gaza Strip. The ANN model considered eleven significant parameters as independent input variables affected on one dependent output variable "project cost". Neurosolution software was used to train the models. The results of the trained models indicated that neural network reasonably succeeded in estimating the cost of building projects without the need for more detailed drawings. The average error of test dataset for the adapted model was largely acceptable (less than 6%). The performed sensitivity analysis showed that the area of typical floor and number of floors are the most influential parameters in building cost. One of the main recommendations of this research is to join the developed model with cost index to give an accurate estimate in any time. In addition, it encourages all parties involved in construction industry to pay more attention for developing ANN in cost estimation by archiving all projects data, and conducting more studies and workshops to obtain maximum advantage of this new approach and join more outputs in a model.