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

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

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


Financial institutions obtain enormous amounts of data about client transactions and money transfers, which can be considered as a large graph dynamically changing in time. In this work, we focus on the task of predicting new interactions in the network of bank clients and treat it as a link prediction problem. We propose a new graph neural network model, which uses not only the topological structure of the network but rich time-series data available for the graph nodes and edges. We evaluate the developed method using the data provided by a large European bank for several years. The proposed model outperforms the existing approaches, including other neural network models, with a significant gap in ROC AUC score on link prediction problem and also allows to improve the quality of credit scoring.

Original languageEnglish
Pages (from-to)135-145
Number of pages11
JournalInternational Journal of Data Science and Analytics
Issue number2
Publication statusPublished - Aug 2021


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


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

Cite this