Contractor pre-qualification model: State-of-the-art

摘要

Contractor pre-qualification is characterized as a multi-criteria problem with uncertain inputs. The criteria used for contractor pre-qualification include qualitative and quantitative information. Owing to the nature of pre-qualification which depends on subjective judgements of construction professionals; it becomes an art rather than a science. Further, there is an inherent non-linear relationship between the input and the output of contractor's pre-qualification models. In an attempt to find the-state-of-the-art model that can meet most characteristics of the contractor's pre-qualification process, the published literature on contractor's pre-qualification models were surveyed. Several approaches are found within the literature. This paper suggests a state-of-the-art model by using a hybrid model, combining the merits of Analytical Hirarchy Process (AHP), Neural Network (NN) and Genetic Algorithm (GA) in one consolidated model which is able to overcome the published models limitations. It is expected that the proposed Genetic-Neural Network (GNN) model will overcome most of the disadvantages of published models, particularly the accuracy of the model outputs and the prediction of the contractor's performance. Also, it gives a chance to improve the client expectation for project success through selecting contractors that are able to meet their objectives.