Conceptual cost estimating is typically completed early in the project lifecycle when little design work has been completed. Because little information is known at this early stage, the estimate usually deviates substantially from the actual construction cost. Therefore, the objective of this research is to develop a conceptual cost estimate model for bridge infrastructure projects. In this study, a systematic literature review and meta-analysis of Mean Average Percentage Errors (MAPEs) of cost models was undertaken to identify the various cost estimation methods, the input variables that have adopted in the development of models and determine the impact of cost estimation method on the accuracy of cost prediction. The research study utilized regression analysis, decision tree and random forest methods for cost prediction of Wisconsin bridges. A comparison of the three models that were developed revealed that random forest cost estimation method yielded better cost prediction.