Neural Network Modeling of Highway Construction Costs

Abstract

The objective of this research was to develop a procedure that estimates the escalation of highway construction costs over time. An artificial neural network model was developed which relates overall highway construction costs, described in terms of a highway construction cost index, to the cost of construction material, labor, and equipment, the characteristics of the contract and the contracting environment prevailing at the time the contract was let. Results demonstrate that the model is able to replicate past highway construction cost trends in Louisiana with reasonable accuracy. Future construction input costs are estimated from commercially available forecasts of indicator variables closely associated with the price of construction labor, construction equipment, and a representative set of highway construction materials. Future contract characteristics and the contracting environment that is likely to exist in the future are estimated from past trends or stipulated to be consistent with policy decisions in the future. The predictions produced by the model estimate that highway construction costs in Louisiana will double between 1998 and 2015.