KNOWLEDGE-BASED DSS FOR CONSTRUCTION CONTRACTOR PRESCREENING

This paper presents the development of a knowledge-based decision supp ort system for predicting construction contract bond claims using cont ractor financial data. The learning and refining sub-system of the pro posed DSS employs Inductive Learning and Neural Networks to extract th e problem solving knowledge to catch the contractor's deteriorating fi nancial condition. The acquired knowledge is stored in the knowledge s ub-system and continually updated to incorporate recent additional inf ormation. This acquired knowledge augments the existing statistical mo dels including multiple discriminate analysis, regression, and logisti c regression models. We propose a framework for integrating fragmented models and knowledge into a DSS so that sureties can analyze the outc ome of each model and knowledge in what-if manner. Moreover, proposed DSS is equipped with the meta-knowledge selecting the most suitable mo dels and knowledge for the given situation intelligently thus providin g peer-opinion for the sureties.