Predicting Owner's Contingency for Transportation Construction Projects Using Intelligent Computing Techniques

Construction projects involve many uncertainties and risks in all phases. As a result, all types of construction projects, including transportation projects, have historically experienced significant cost increases. Project contingencies are important items in the cost estimate for compensating invisible and unforeseen risks against underestimating project costs and overrunning budgets. Generally, a contingency is represented as a fixed percentage of project cost (e.g., 5% of the contract value). However, it is not appropriate to apply this deterministic method to all construction projects because it provides an arbitrary percentage value based on only project costs. In this paper, a method for predicting the owner's contingency for transportation construction projects is proposed by identifying factors that affect the owner's contingency and using artificial neural network (ANN) techniques to predict these values. Transportation projects sponsored by the FDOT (Florida Department of Transportation) and completed from 2004 to 2006 are used for this study. The finding shows the viability of the artificial neural network approach to predict the owner's contingency for transportation projects. These predictions in turn can be used to better manage project contingency requirements and allow for additional projects to be brought online at a faster pace.