Opin vísindi

Fraud Detection of Bulk Cargo Theft in Port Using Bayesian Network Models

Show simple item record

dc.contributor Háskólinn í Reykjavík
dc.contributor Reykjavik University
dc.contributor.author Song, Rongjia
dc.contributor.author Huang, Lei
dc.contributor.author Cui, Weiping
dc.contributor.author Óskarsdóttir, María
dc.contributor.author Vanthienen, Jan
dc.date.accessioned 2020-11-30T16:03:01Z
dc.date.available 2020-11-30T16:03:01Z
dc.date.issued 2020-02-05
dc.identifier.citation Song, R., Huang, L., Cui, W., Oskarsdottir, M., & Vanthienen, J. (2020). Fraud Detection of Bulk Cargo Theft in Port Using Bayesian Network Models. Applied Sciences-Basel, 10(3), 1056. https://doi.org/10.3390/app10031056
dc.identifier.issn 2076-3417 (eISSN)
dc.identifier.uri https://hdl.handle.net/20.500.11815/2261
dc.description Publisher's version (útgefin grein)
dc.description.abstract The fraud detection of cargo theft has been a serious issue in ports for a long time. Traditional research in detecting theft risk is expert- and survey-based, which is not optimal for proactive prediction. As we move into a pervasive and ubiquitous paradigm, the implications of external environment and system behavior are continuously captured as multi-source data. Therefore, we propose a novel data-driven approach for formulating predictive models for detecting bulk cargo theft in ports. More specifically, we apply various feature-ranking methods and classification algorithms for selecting an effective feature set of relevant risk elements. Then, implicit Bayesian networks are derived with the features to graphically present the relationship with the risk elements of fraud. Thus, various binary classifiers are compared to derive a suitable predictive model, and Bayesian network performs best overall. The resulting Bayesian networks are then comparatively analyzed based on the outcomes of model validation and testing, as well as essential domain knowledge. The experimental results show that predictive models are effective, with both accuracy and recall values greater than 0.8. These predictive models are not only useful for understanding the dependency between relevant risk elements, but also for supporting the strategy optimization of risk management.
dc.format.extent 1056
dc.language.iso en
dc.publisher MDPI AG
dc.relation.ispartofseries Applied Sciences;10(3)
dc.rights info:eu-repo/semantics/openAccess
dc.subject Fraud detection
dc.subject Predictive modeling
dc.subject Bulk cargo theft
dc.subject Bayesian network
dc.subject Port
dc.subject Fjársvik
dc.subject Gagnagreining
dc.subject Spálíkön
dc.subject Farmur
dc.subject Þjófnaðir
dc.subject Hafnir
dc.title Fraud Detection of Bulk Cargo Theft in Port Using Bayesian Network Models
dc.type info:eu-repo/semantics/article
dcterms.license This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution(CC BY) license (http://creativecommons.org/licenses/by/4.0/).
dc.description.version "Peer Reviewed"
dc.identifier.doi 10.3390/app10031056
dc.relation.url https://www.mdpi.com/2076-3417/10/3/1056/pdf
dc.contributor.department Tölvunarfræðideild (HR)
dc.contributor.department Department of Computer Science (RU)
dc.contributor.school Tæknisvið (HR)
dc.contributor.school School of Technology (RU)

Files in this item

This item appears in the following Collection(s)

Show simple item record