Bootstrap Aggregated Case-Based Reasoning Method for Conceptual Cost Estimation

Conceptual cost estimation is an important step in project feasibility decisions when there not enough information on detailed design and requirements. Methods that enable quick reasonably accurate conceptual estimates are crucial for achieving successful the early stages of construction projects. For this reason, numerous machine learning methods proposed literature use different mechanisms. In recent years, case-based reasoning (CBR) method has received particular attention projects similarity-based principles. Despite fact CBR provides a powerful practical alternative estimation, one main criticisms about its low prediction performance sufficient number cases. This paper presents bootstrap aggregated advancement research, particularly limited training cases available. The designed so can learn from diverse set data even evaluated using three sets. results revealed new better than existing method. Since majority made with cases, contribution to research practice by improving estimating.