Revised case-based reasoning model development based on multiple regression analysis for railroad bridge construction

Many large construction projects are being carried out simultaneously. The accuracy of the budget allocated in the planning phase of such projects is considered a key element in efficient budget use, but lack of information during the planning phase results in the inaccurate estimation of the construction cost. Thus, it is necessary to devise a method that improves the accuracy of construction cost estimation in the planning phase. Although recently there has been an increase in the use of case-based reasoning (CBR) for construction cost estimation, the use of CBR tends to reduce the accuracy of the estimated construction cost, unless there is sufficient similarity between the cases stored in the database and the retrieved cases. Therefore, a revised CBR model based on the regression analysis model was developed in this study, and a calculation model capable of estimating the construction cost in the planning phase was developed with a focus on railroad-bridge construction projects. To verify the revised CBR model, five case studies were conducted. The results showed that the revised CBR model reduced the construction cost error rate of the proposed CBR model by 16.2%. In particular, it is expected that the revised CBR model will be useful when there is a lack of similarity between the cases stored in the database and the retrieved cases.