Monitoring Liquidity Management of Banks With Recurrent Neural Networks
- PDF / 1,489,981 Bytes
- 24 Pages / 439.37 x 666.142 pts Page_size
- 30 Downloads / 187 Views
Monitoring Liquidity Management of Banks With Recurrent Neural Networks Ron Triepels1 · Hennie Daniels2,3 · Ron Berndsen2,4 Accepted: 23 July 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Monitoring liquidity management of banks is one of the prime tasks of central banks. A bank that manages its liquidity inadequately can severely harm its liquidity position and potentially threaten the stability of the entire financial system. Central banks try to anticipate these risks by carefully monitoring the liquidity management of banks in large-value payment systems (LVPSs). Typically, they do this based on statistical methods in which various risk indicators related to the liquidity usage of banks are calculated from the transaction log of an LVPS. These indicators need to be manually analyzed by payment experts to find irregularities that could signal potential risks. Although statistical methods provide much insight into the liquidity management of banks, they do not scale well to the large number of banks that are subject to risk monitoring and the high velocity by which payments are nowadays settled. In this paper, we investigate whether the liquidity management of banks can be monitored more efficiently by anomaly detection. We construct different probabilistic classifiers that classify delta sequences of banks by the corresponding bank. A delta sequence captures the change in the liquidity position of a bank in an LVPS throughout a given day. Accordingly, anomalies in the intraday liquidity usage of banks are detected by determining whether the classifiers misclassify recent delta sequences that were not used to train the classifiers. Our results show that recurrent neural networks are well suited to perform this classification task and detect many irregularities in payment behavior that are interesting for the supervisors and operators of an LVPS. Keywords Anomaly detection · Recurrent neural networks · Liquidity management · Large-value payment systems * Ron Triepels [email protected] 1
De Nederlandsche Bank, Westeinde 1, Amsterdam, The Netherlands
2
Tilburg University, Warandelaan 2, Tilburg, The Netherlands
3
Erasmus University, Burgemeester Oudlaan 50, Rotterdam, The Netherlands
4
LCH Clearnet, 33 Aldgate High Street, London, UK
13
Vol.:(0123456789)
R. Triepels et al.
1 Introduction Inadequate liquidity management by banks has been identified as one of the leading causes of financial instability (Heijmans and Heuver 2014). Liquidity management is the task of carefully planning how a bank should use its available liquidity to execute its payments during the day. A bank that does not manage its liquidity adequately exposes itself to various financial risks that threaten its liquidity position and that of many other banks due to contagion effects (Allen and Gale 2000). In the worst case, this can trigger a banking crisis in which multiple banks default. The impact of a banking crisis on an economy has proven to be significant. Estimates show that the
Data Loading...
