A knowledge-based risk management tool for construction projects using case-based reasoning

doi:10.1016/j.eswa.2021.114776

Return

A knowledge-based risk management tool for construction projects using case-based reasoning

2021-07-01

Ozan Okudan *

Cenk Budayan

İrem Dikmen

DOI：10.1016/j.eswa.2021.114776

Original

Save

View PDF

Abstract

En 中文

Construction projects are often deemed as complex and high-risk endeavours, mostly because of their vulnerability to external conditions as well as project-related uncertainties. Risk management (RM) is a critical success factor for companies operating in the construction industry. RM is a knowledge-intensive process that requires effective management of risk-related knowledge. Although some research has already been conducted to develop tools to support knowledge-based RM processes, most of these tools ignore some critical features, such as live knowledge capture, web-based platform for knowledge sharing and effective case retrieval for learning from past projects. Moreover, several RM phases, such as risk identification, analysis, response and monitoring are not usually integrated. Thus, this study aims to bridge these gaps by developing a knowledge-based RM tool (namely, CBRisk) via case-based reasoning (CBR). CBRisk has been developed as a web-based tool that supports the cyclic RM process and utilises an effective case retrieval method considering a comprehensive list of project similarity features in the form of fuzzy linguistic variables. Finally, the developed tool was evaluated and validated by conducting black-box testing and expert review meeting. Results demonstrated that CBRisk has a considerable potential to enhance the effectiveness of RM in construction projects and may be used in other project-based industries with minimal modifications.

Keywords:

Artificial intelligence

Machine learning

Knowledge-based risk management

Risk management

Knowledge management

Case-based reasoning

Web-based tool

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.