Abstracts – Browse Results

Search or browse again.

Click on the titles below to expand the information about each abstract.
Viewing 1 results ...

Al-Sobiei, O S, Arditi, D and Polat, G (2005) Predicting the risk of contractor default in Saudi Arabia utilizing artificial neural network (ANN) and genetic algorithm (GA) techniques. Construction Management and Economics, 23(04), 423-30.

  • Type: Journal Article
  • Keywords: artificial neural networks; contractor default; genetic algorithms; prediction model
  • ISBN/ISSN: 0144-6193
  • URL: https://doi.org/10.1080/01446190500041578
  • Abstract:

    The construction project is subject to several risks, one of the most important of which is contractor default because contractor default may increase the final project cost considerably. In the US construction industry, owners commonly shield themselves from the risk of contractor default by transferring this risk to the contractor, who in turn transfers this risk to a surety company. On the other hand, the General Directorate of Military Works (GDMW) of the Kingdom of Saudi Arabia retains the risk of contractor default rather than transferring it to a third party. An artificial neural network (ANN) and a genetic algorithm (GA) are used in this study to predict the risk of contractor default in construction projects undertaken for the Saudi armed forces. Based on this prediction, the Saudi GDMW can make a decision to engage or not to engage the services of a contractor. In case the models are not able to generate reliable predictions (or generate contradictory outcomes), the GDMW will have to augment its budget with contingency funds to be used in the event of contractor default. The outcome of this study is of particular relevance to construction owners because it proposes an approach that can allow them to replace an indiscriminate blanket policy by a policy that is rational, effective, prudent and economical.