A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Harnessing Machine Learning for Classifying Economic Damage Trends in Transportation Infrastructure Projects
Given the highly visible nature, transportation infrastructure construction projects are often exposed to numerous unexpected events, compared to other types of construction projects. Despite the importance of predicting financial losses caused by risk, it is still difficult to determine which risk factors are generally critical and when these risks tend to occur, without benchmarkable references. Most of existing methods are prediction-focused, project type-specific, while ignoring the timing aspect of risk. This study filled these knowledge gaps by developing a neural network-driven machine-learning classification model that can categorize causes of financial losses depending on insurance claim payout proportions and risk occurrence timing, drawing on 625 transportation infrastructure construction projects including bridges, roads, and tunnels. The developed network model showed acceptable classification accuracy of 74.1%, 69.4%, and 71.8% in training, cross-validation, and test sets, respectively. This study is the first of its kind by providing benchmarkable classification references of economic damage trends in transportation infrastructure projects. The proposed holistic approach will help construction practitioners consider the uncertainty of project management and the potential impact of natural hazards proactively, with the risk occurrence timing trends. This study will also assist insurance companies with developing sustainable financial management plans for transportation infrastructure projects.
Harnessing Machine Learning for Classifying Economic Damage Trends in Transportation Infrastructure Projects
Given the highly visible nature, transportation infrastructure construction projects are often exposed to numerous unexpected events, compared to other types of construction projects. Despite the importance of predicting financial losses caused by risk, it is still difficult to determine which risk factors are generally critical and when these risks tend to occur, without benchmarkable references. Most of existing methods are prediction-focused, project type-specific, while ignoring the timing aspect of risk. This study filled these knowledge gaps by developing a neural network-driven machine-learning classification model that can categorize causes of financial losses depending on insurance claim payout proportions and risk occurrence timing, drawing on 625 transportation infrastructure construction projects including bridges, roads, and tunnels. The developed network model showed acceptable classification accuracy of 74.1%, 69.4%, and 71.8% in training, cross-validation, and test sets, respectively. This study is the first of its kind by providing benchmarkable classification references of economic damage trends in transportation infrastructure projects. The proposed holistic approach will help construction practitioners consider the uncertainty of project management and the potential impact of natural hazards proactively, with the risk occurrence timing trends. This study will also assist insurance companies with developing sustainable financial management plans for transportation infrastructure projects.
Harnessing Machine Learning for Classifying Economic Damage Trends in Transportation Infrastructure Projects
Junseo Bae (author) / Sang-Guk Yum (author) / Ji-Myong Kim (author)
2021
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Overruns in transportation infrastructure projects
| Online Contents | 2014
Overruns in transportation infrastructure projects
| Taylor & Francis Verlag | 2014
An automated machine learning approach for classifying infrastructure cost data
| Wiley | 2024
GEOFOAM TRENDS IN TRANSPORTATION PROJECTS
| British Library Online Contents | 2010