Detection and explanation of anomalies in real-time gross settlement systems by lossy data compression

Ron Triepels, Hennie Daniels, R. Heijmans

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Abstract

In this paper, we discuss how to apply an autoencoder to detect anomalies in payment data derived from an Real-Time Gross Settlement system. Moreover, we introduce a drill-down procedure to measure the extent to which the inflow or outflow of a particular bank explains an anomaly. Experimental results on real-world payment data show that our method can detect the liquidity problems of a bank when it was subject to a bank run with reasonable accuracy.
Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Enterprise Information Systems (ICEIS 2017)
EditorsSlimane Hammoudi, Michal Smialek, Olivier Camp, Joaquim Filipe
Place of PublicationCham
PublisherSpringer Verlag
Pages145-161
ISBN (Print)9783319933740
Publication statusPublished - 2018

Publication series

NameLecture Notes in Business Information Processing
Volume321

Keywords

  • anomaly detection
  • autoencoders
  • payment behavior
  • real-time gross settlement systems

Fingerprint

Dive into the research topics of 'Detection and explanation of anomalies in real-time gross settlement systems by lossy data compression'. Together they form a unique fingerprint.

Cite this