A Bayesian Classifier Based on Constraints of Ordering of Variables for Fraud Detection

Pedro Shiguihara-Juarez, Nils Murrugarra-Llerena

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Fraud detection is important for financial institutions and the society. Supervised machine learning techniques were applied for fraud detection. However, mostly discriminative techniques were applied on these problems. Probabilistic graphical models can also detect fraud, providing also a graphical representation of its reasoning scheme as a graph. We proposed a method to generate a probabilistic graphical model for fraud detection, using constraints related to the domain. We achieved 99.272% of accuracy and we outperformed other baselines techniques of probabilistic graphical models. We demonstrated that constraints are important to tackle complex problem such a fraud detection.

Original languageEnglish
Title of host publication2018 Congreso Internacional de Innovacion y Tendencias en Ingenieria, CONIITI 2018 - Proceedings
EditorsCarlos Andres Lozano-Garzon
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538681312
DOIs
StatePublished - 21 Dec 2018
Externally publishedYes
Event4th Innovation and Trends in Engineering Congress, CONIITI 2018 - Bogota, Colombia
Duration: 3 Oct 20185 Oct 2018

Publication series

Name2018 Congreso Internacional de Innovacion y Tendencias en Ingenieria, CONIITI 2018 - Proceedings

Conference

Conference4th Innovation and Trends in Engineering Congress, CONIITI 2018
Country/TerritoryColombia
CityBogota
Period3/10/185/10/18

Keywords

  • Bayesian Networks
  • Fraud Detection
  • Probabilistic Graphical Models

Fingerprint

Dive into the research topics of 'A Bayesian Classifier Based on Constraints of Ordering of Variables for Fraud Detection'. Together they form a unique fingerprint.

Cite this