Data mining algorithms for risk detection in bank loans

Alvaro Talavera, Luis Cano, David Paredes, Mario Chong

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

Abstract

This article proposes a new approach on detection of fraudulent credit operations applying computational intelligence techniques. We use a dataset of historical data of customers from a financial entity and we split it to train a classification and clustering algorithm. We train a radial basis function network to classify clients that commit or not credit fraud. Then, we build a Fuzzy c-means clustering to group data points to create customer profiles. This algorithm has the capacity of grouping the data inside clusters and assigning a degree of membership to the points outside the clusters. Subsequently, the trained classification algorithm is applied to the clusters to provide additional information about customer profiles. We demonstrate good performance for fraudulent credit operations and identification of customer profiles.
Original languageEnglish
Title of host publicationInformation Management and Big Data - 5th International Conference, SIMBig 2018, Proceedings
EditorsHugo Alatrista-Salas, Denisse Muñante, Juan Antonio Lossio-Ventura
Pages151-159
Number of pages9
ISBN (Electronic)9783030116798
DOIs
StatePublished - 1 Jan 2019
EventCommunications in Computer and Information Science -
Duration: 1 Jan 2019 → …

Publication series

NameCommunications in Computer and Information Science
Volume898
ISSN (Print)1865-0929

Conference

ConferenceCommunications in Computer and Information Science
Period1/01/19 → …

Bibliographical note

Publisher Copyright:
© 2019, Springer Nature Switzerland AG.

Keywords

  • Finance profiles
  • Fuzzy C-means
  • Radial basis function networks
  • Risk detection

Fingerprint

Dive into the research topics of 'Data mining algorithms for risk detection in bank loans'. Together they form a unique fingerprint.

Cite this