A support vector machine model for contractor prequalification

In complex and high value projects, prequalification is crucial for both contractors and clients, as it targets towards best value delivery through qualification safeguards and streamlined competition among potential candidates. Due the complex nature of the procurement problems such as prequalification exercises, the robust models are rarely attempted. The research reported in this paper presents an overview of potential suitability of Support Vector Machine (SVM) method for contractor/consultant prequalification transactions in the construction project procurements. Furthermore, the performance of SVM is compared with specific artificial neural network outcomes. The results obtained from practical datasets indicate encouraging potentials for SVM applications in the procurement problems such as prequalification and contractor selection. Hence, a SVM-based decision support framework is proposed. © 2008 Elsevier B.V. All rights reserved.