Developing Cost Estimation Models for Road Rehabilitation and Reconstruction: Case Study of Projects in Europe and Central Asia

Abstract

This paper presents the development of prediction models for the unit costs of road works that could be applied to strategic planning of road works at the network level. A specialized data set was used, which was generated under a World Bank study that included 200 road work contracts from 14 countries in Europe and Central Asia (ECA) and signed between 2000 and 2010. Two techniques were used for model development: multiple regression analysis and artificial neural networks. Classification trees were used as an intermediate step to evaluate the correctness of the selected parameters. A total of 19 variables, divided into three groups (oil-price related, country-related, and project-related variables), were tested for their influence on unit cost of asphalt concrete (AC) and road rehabilitation and reconstruction (RRR) costs. The analysis results showed that the level of corruption and the economic environment in a country have a significant effect on both costs of AC and RRR. The resulting models could be particularly useful for the planning and optimization of work on road networks in ECA countries. However, the approach and methodology used for model developments may be applied generally.