Predictive models to estimate construction and life-cycle cost of conventional and prefabricated bridges during early design phases

State DOTs often need to decide during the early design phase whether to build their bridges using conventional or prefabricated construction methods based on overall cost effectiveness. This often requires DOTs to develop reliable cost estimates of these alternative construction methods with only limited available data during the early design phase. To support DOTs in this challenging task, this paper presents the development of a practical decision support tool that integrates novel bridge cost estimating models. These models were developed using stepwise, LASSO, and best subset regression techniques and a dataset of 241 conventional and prefabricated bridges. The developed LASSO model outperformed the two other models, achieving a mean absolute percentage error of 12.3% for conventional and 14.4% for prefabricated bridge projects. The developed decision support tool and its cost estimating models are expected to support bridge planners in identifying the most cost-effective bridge construction method during the early design phase.