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

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.

Business process redesign towards IoT-enabled context-awareness: the case of a Chinese bulk port

“…Based on the long-term cooperation between our research group and a Chinese seaport in the south, which is one of the largest hub ports with its throughput ranking among the top 5 in mainland China, comprehensive IT research have been done to improve operations especially for bulk cargo (Wang et al, 2014). In particular, serious operational problems could happen in the truck pick-up cargo process because of a lack of context-awareness, such as cargo loss, pick-up fraud, etc (Song et al, 2020). Thus, the storage yard apartment arranges frequent manual inspection during the process as the countermeasure, which brings large expense, subjectivity and hysteresis.…”

“…A system is designed and implemented for the risk early-warning for the truck pick-up cargo process by visualizing meaningful information during the process execution including the record of an empty truck weight, the truck route in port, the real-time risk score of trucks in port, trucks in monitoring, etc. This early-warning system embeds the algorithm proposed in Song et al (2020) and employs a B/S architecture that consists of data layer, application layer and presentation layer. Users can manipulate on a browser for exchanging with databases through a web server.…”

“…The fraud detection of cargo theft has been a serious issue in ports for a long time. Rather than expert- and survey-based methods in detecting theft risk in traditional research, we proposed a novel data-driven approach for formulating predictive models in order to detect bulk cargo theft in ports in Song et al. (2020).…”

Možnosti Zvýšenia Prekládky Suchého Hromadného Voľne Loženého Nákladu v Prístavoch

“…Medzi najbežnejšie druhy tohto nákladu v námornej doprave patrí hlavne uhlie, železná ruda, bauxit, kukurica, sója, obilniny a pod. Song et. al.…”

Detecting and Analyzing Fraudulent Patterns of Financial Statement for Open Innovation Using Discretization and Association Rule Mining

“…The detection efficiency of the CHAID-CART model was the best, with an overall accuracy of 87.97% (fraudulent financial statement detection accuracy was 92.69%). Song et al [12] studied bulk cargo theft at ports using the Bayesian network method. They also applied a feature ranking method for selecting the important features of relevant risk.…”