Toll fraud detection of voip services via an ensemble of novelty detection algorithms

Pilsung Kang, Kyungil Kim, Namwook Cho

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Communications fraud has been dramatically increasing with the development of communication technologies and the increasing use of global communications, resulting in substantial losses to telecommunication industry. Due to the widespread deployment of voice over internet protocol (VoIP), the fraud of VoIP has been one of major concerns of the communications industry. In this paper, we develop toll fraud detection systems based on an ensemble of novelty detection algorithms using call detail records (CDRs). Initially, based on actual CDRs collected from a Korean VoIP service provider for a month, candidate explanatory variables are created using historical fraud patterns. Then, a total of five novelty detection algorithms are trained for each week to identify toll frauds during the following week. Subsequently, fraud detection performance improvements are attempted by selecting significant explanatory variables using genetic algorithm (GA) and constructing an ensemble of novelty detection models. Experimental results show that the proposed framework is practically effective in that most of the toll frauds can be detected with high recall and precision rates. It is also found that the variable selection using GA enables us to build not only more accurate but also more efficient fraud detection models. Finally, an ensemble of novelty detection models further boosts the fraud detection ability especially when the fraud rate is relatively low.

Original languageEnglish
Pages (from-to)213-222
Number of pages10
JournalInternational Journal of Industrial Engineering : Theory Applications and Practice
Volume22
Issue number2
Publication statusPublished - 2015 Jan 1

Fingerprint

Internet protocols
Communication
Genetic algorithms
Telecommunication industry
Industry

Keywords

  • Call detail records (cdrs)
  • Ensemble
  • Genetic algorithm (ga)
  • Novelty detection
  • Toll fraud detection
  • Voip service

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Toll fraud detection of voip services via an ensemble of novelty detection algorithms. / Kang, Pilsung; Kim, Kyungil; Cho, Namwook.

In: International Journal of Industrial Engineering : Theory Applications and Practice, Vol. 22, No. 2, 01.01.2015, p. 213-222.

Research output: Contribution to journalArticle

@article{a212947e4b25449886258e55fa0b94a1,
title = "Toll fraud detection of voip services via an ensemble of novelty detection algorithms",
abstract = "Communications fraud has been dramatically increasing with the development of communication technologies and the increasing use of global communications, resulting in substantial losses to telecommunication industry. Due to the widespread deployment of voice over internet protocol (VoIP), the fraud of VoIP has been one of major concerns of the communications industry. In this paper, we develop toll fraud detection systems based on an ensemble of novelty detection algorithms using call detail records (CDRs). Initially, based on actual CDRs collected from a Korean VoIP service provider for a month, candidate explanatory variables are created using historical fraud patterns. Then, a total of five novelty detection algorithms are trained for each week to identify toll frauds during the following week. Subsequently, fraud detection performance improvements are attempted by selecting significant explanatory variables using genetic algorithm (GA) and constructing an ensemble of novelty detection models. Experimental results show that the proposed framework is practically effective in that most of the toll frauds can be detected with high recall and precision rates. It is also found that the variable selection using GA enables us to build not only more accurate but also more efficient fraud detection models. Finally, an ensemble of novelty detection models further boosts the fraud detection ability especially when the fraud rate is relatively low.",
keywords = "Call detail records (cdrs), Ensemble, Genetic algorithm (ga), Novelty detection, Toll fraud detection, Voip service",
author = "Pilsung Kang and Kyungil Kim and Namwook Cho",
year = "2015",
month = "1",
day = "1",
language = "English",
volume = "22",
pages = "213--222",
journal = "International Journal of Industrial Engineering : Theory Applications and Practice",
issn = "1072-4761",
publisher = "University of Cincinnati",
number = "2",

}

TY - JOUR

T1 - Toll fraud detection of voip services via an ensemble of novelty detection algorithms

AU - Kang, Pilsung

AU - Kim, Kyungil

AU - Cho, Namwook

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Communications fraud has been dramatically increasing with the development of communication technologies and the increasing use of global communications, resulting in substantial losses to telecommunication industry. Due to the widespread deployment of voice over internet protocol (VoIP), the fraud of VoIP has been one of major concerns of the communications industry. In this paper, we develop toll fraud detection systems based on an ensemble of novelty detection algorithms using call detail records (CDRs). Initially, based on actual CDRs collected from a Korean VoIP service provider for a month, candidate explanatory variables are created using historical fraud patterns. Then, a total of five novelty detection algorithms are trained for each week to identify toll frauds during the following week. Subsequently, fraud detection performance improvements are attempted by selecting significant explanatory variables using genetic algorithm (GA) and constructing an ensemble of novelty detection models. Experimental results show that the proposed framework is practically effective in that most of the toll frauds can be detected with high recall and precision rates. It is also found that the variable selection using GA enables us to build not only more accurate but also more efficient fraud detection models. Finally, an ensemble of novelty detection models further boosts the fraud detection ability especially when the fraud rate is relatively low.

AB - Communications fraud has been dramatically increasing with the development of communication technologies and the increasing use of global communications, resulting in substantial losses to telecommunication industry. Due to the widespread deployment of voice over internet protocol (VoIP), the fraud of VoIP has been one of major concerns of the communications industry. In this paper, we develop toll fraud detection systems based on an ensemble of novelty detection algorithms using call detail records (CDRs). Initially, based on actual CDRs collected from a Korean VoIP service provider for a month, candidate explanatory variables are created using historical fraud patterns. Then, a total of five novelty detection algorithms are trained for each week to identify toll frauds during the following week. Subsequently, fraud detection performance improvements are attempted by selecting significant explanatory variables using genetic algorithm (GA) and constructing an ensemble of novelty detection models. Experimental results show that the proposed framework is practically effective in that most of the toll frauds can be detected with high recall and precision rates. It is also found that the variable selection using GA enables us to build not only more accurate but also more efficient fraud detection models. Finally, an ensemble of novelty detection models further boosts the fraud detection ability especially when the fraud rate is relatively low.

KW - Call detail records (cdrs)

KW - Ensemble

KW - Genetic algorithm (ga)

KW - Novelty detection

KW - Toll fraud detection

KW - Voip service

UR - http://www.scopus.com/inward/record.url?scp=84956973199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956973199&partnerID=8YFLogxK

M3 - Article

VL - 22

SP - 213

EP - 222

JO - International Journal of Industrial Engineering : Theory Applications and Practice

JF - International Journal of Industrial Engineering : Theory Applications and Practice

SN - 1072-4761

IS - 2

ER -