Linking bank clients using graph neural networks powered by rich transactional data: Extended abstract

Valentina Shumovskaia, Kirill Fedyanin, Ivan Sukharev, Dmitry Berestnev, Maxim Panov

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

8 Citations (Scopus)

Abstract

Each day bank clients conduct numerous operations, such as purchasing goods or transferring money to other clients. These interactions can be interpreted as a graph dynamically changing over time. This work focuses on the task of predicting new interactions in the network of bank clients and treats it as a link prediction problem. We propose an architecture for the graph convolutional network to efficiently solve the link prediction problem for this type of data. Our model uses recurrent neural networks to leverage the time-series data in both nodes and edges and effectively scales to the graphs with millions of nodes. We evaluate the model on the data provided for several years by a large European bank. The obtained results show that the model outperforms the existing approaches. The current paper is an extended abstract for the work [5].

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020
EditorsGeoff Webb, Zhongfei Zhang, Vincent S. Tseng, Graham Williams, Michalis Vlachos, Longbing Cao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages787-788
Number of pages2
ISBN (Electronic)9781728182063
DOIs
Publication statusPublished - Oct 2020
Event7th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2020 - Virtual, Sydney, Australia
Duration: 6 Oct 20209 Oct 2020

Publication series

NameProceedings - 2020 IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020

Conference

Conference7th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2020
Country/TerritoryAustralia
CityVirtual, Sydney
Period6/10/209/10/20

Keywords

  • Credit scoring
  • Graph neural network
  • Link prediction
  • Recurrent neural network
  • Transactional data

Fingerprint

Dive into the research topics of 'Linking bank clients using graph neural networks powered by rich transactional data: Extended abstract'. Together they form a unique fingerprint.

Cite this