Data driven fraud detection in international shipping

Ron Triepels, Hennie Daniels, A.J. Feelders

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Document fraud constitutes a growing problem in international shipping. Shipping documentation may be deliberately manipulated to avoid shipping restrictions or customs duties. Well-known examples of such fraud are miscoding and smuggling. These are cases in which the documentation of a shipment does not correctly or entirely describe the goods in transit. In an attempt to reduce the risks of document fraud, shipping companies and customs authorities typically perform random audits to check the accompanying documentation of shipments. Although these audits detect many fraud schemes, they are quite labor intensive and do not scale to the massive amounts of cargo that is shipped each day. This paper investigates whether intelligent fraud detection systems can improve the detection of miscoding and smuggling by analyzing large sets of historical shipment data. We develop a Bayesian network that predicts the presence of goods on the cargo list of shipments. The predictions of the Bayesian network are compared with the accompanying documentation of a shipment to determine whether document fraud is perpetrated. We also show how a set of discriminative models can be derived from the topology of the Bayesian network and perform the same fraud detection task. Our experimental results show that intelligent fraud detection systems can considerably improve the detection of miscoding and smuggling compared to random audits.
Original languageEnglish
Pages (from-to)193-202
JournalExpert Systems with Applications
Volume99
DOIs
Publication statusPublished - Jun 2018

Fingerprint

Freight transportation
Bayesian networks
Topology
Personnel
Industry

Keywords

  • international shipping
  • fraud detection
  • probablistic classification
  • Bayesian networks
  • logistic regression
  • neural networks

Cite this

Triepels, Ron ; Daniels, Hennie ; Feelders, A.J. / Data driven fraud detection in international shipping. In: Expert Systems with Applications. 2018 ; Vol. 99. pp. 193-202.
@article{b4025a1190cc4521bddc27a3f42ab0ad,
title = "Data driven fraud detection in international shipping",
abstract = "Document fraud constitutes a growing problem in international shipping. Shipping documentation may be deliberately manipulated to avoid shipping restrictions or customs duties. Well-known examples of such fraud are miscoding and smuggling. These are cases in which the documentation of a shipment does not correctly or entirely describe the goods in transit. In an attempt to reduce the risks of document fraud, shipping companies and customs authorities typically perform random audits to check the accompanying documentation of shipments. Although these audits detect many fraud schemes, they are quite labor intensive and do not scale to the massive amounts of cargo that is shipped each day. This paper investigates whether intelligent fraud detection systems can improve the detection of miscoding and smuggling by analyzing large sets of historical shipment data. We develop a Bayesian network that predicts the presence of goods on the cargo list of shipments. The predictions of the Bayesian network are compared with the accompanying documentation of a shipment to determine whether document fraud is perpetrated. We also show how a set of discriminative models can be derived from the topology of the Bayesian network and perform the same fraud detection task. Our experimental results show that intelligent fraud detection systems can considerably improve the detection of miscoding and smuggling compared to random audits.",
keywords = "international shipping, fraud detection, probablistic classification, Bayesian networks, logistic regression, neural networks",
author = "Ron Triepels and Hennie Daniels and A.J. Feelders",
year = "2018",
month = "6",
doi = "10.1016/j.eswa.2018.01.007",
language = "English",
volume = "99",
pages = "193--202",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",

}

Data driven fraud detection in international shipping. / Triepels, Ron; Daniels, Hennie; Feelders, A.J.

In: Expert Systems with Applications, Vol. 99, 06.2018, p. 193-202.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Data driven fraud detection in international shipping

AU - Triepels, Ron

AU - Daniels, Hennie

AU - Feelders, A.J.

PY - 2018/6

Y1 - 2018/6

N2 - Document fraud constitutes a growing problem in international shipping. Shipping documentation may be deliberately manipulated to avoid shipping restrictions or customs duties. Well-known examples of such fraud are miscoding and smuggling. These are cases in which the documentation of a shipment does not correctly or entirely describe the goods in transit. In an attempt to reduce the risks of document fraud, shipping companies and customs authorities typically perform random audits to check the accompanying documentation of shipments. Although these audits detect many fraud schemes, they are quite labor intensive and do not scale to the massive amounts of cargo that is shipped each day. This paper investigates whether intelligent fraud detection systems can improve the detection of miscoding and smuggling by analyzing large sets of historical shipment data. We develop a Bayesian network that predicts the presence of goods on the cargo list of shipments. The predictions of the Bayesian network are compared with the accompanying documentation of a shipment to determine whether document fraud is perpetrated. We also show how a set of discriminative models can be derived from the topology of the Bayesian network and perform the same fraud detection task. Our experimental results show that intelligent fraud detection systems can considerably improve the detection of miscoding and smuggling compared to random audits.

AB - Document fraud constitutes a growing problem in international shipping. Shipping documentation may be deliberately manipulated to avoid shipping restrictions or customs duties. Well-known examples of such fraud are miscoding and smuggling. These are cases in which the documentation of a shipment does not correctly or entirely describe the goods in transit. In an attempt to reduce the risks of document fraud, shipping companies and customs authorities typically perform random audits to check the accompanying documentation of shipments. Although these audits detect many fraud schemes, they are quite labor intensive and do not scale to the massive amounts of cargo that is shipped each day. This paper investigates whether intelligent fraud detection systems can improve the detection of miscoding and smuggling by analyzing large sets of historical shipment data. We develop a Bayesian network that predicts the presence of goods on the cargo list of shipments. The predictions of the Bayesian network are compared with the accompanying documentation of a shipment to determine whether document fraud is perpetrated. We also show how a set of discriminative models can be derived from the topology of the Bayesian network and perform the same fraud detection task. Our experimental results show that intelligent fraud detection systems can considerably improve the detection of miscoding and smuggling compared to random audits.

KW - international shipping

KW - fraud detection

KW - probablistic classification

KW - Bayesian networks

KW - logistic regression

KW - neural networks

U2 - 10.1016/j.eswa.2018.01.007

DO - 10.1016/j.eswa.2018.01.007

M3 - Article

VL - 99

SP - 193

EP - 202

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -