Contractor selection: fuzzy-control approach

Abstract

This paper presents a fuzzy-logic-based system for selecting contractors. This tool, which was based on the fuzzy control technique, was created for the private sector client in traditional design–bid–build projects with one-step selection processes, but its philosophy can also serve other types of clients, industries, contracts, and selection processes. The system develops an assessment of different qualitative and quantitative issues that influence a contractor’s suitability for constructing a specific design in a specific environment (client’s needs and objectives, objectives prioritization, etc.), taking into account the risk of not achieving the client’s objectives. A computer application was developed and validated, including a Delphi analysis with professionals who are experts in contractor selection. The application covers the possibility of using different selection policies, when the essential project objective is cost, time or quality. As part of the validation process, a neural network was developed to prove that the fuzzy-control tool has a behavior that can be recognized by a neural network.