A deep learning approach to dynamic interbank network link prediction
Haici Zhang
Lehman Brothers' failure in 2008 demonstrated the importance of understanding interconnectedness in interbank networks. The interbank market plays a significant role in facilitating market liquidity and providing short-term funding for each other to smooth liquidity shortages. Knowing the trading relationship could also help understand risk contagion among banks. Therefore, future lending relationship prediction is important to understand the dynamic evolution of interbank networks. To achieve the goal, we apply a deep learning framework model of interbank lending to an electronic trading interbank network for temporal trading relationship prediction. There are two important components of the model, which are the Graph convolutional network (GCN) and the Long short-term memory (LSTM) model. The GCN and LSTM components together capture the spatial-temporal information of the dynamic network snapshots. Compared with the Discrete autoregressive model and Dynamic latent space model, our proposed model achieves better performance in both the precrisis and the crisis period.
Year of publication: |
2022
|
---|---|
Authors: | Zhang, Haici |
Subject: | graph convolutional network | interbank network | link prediction | long short-term memory | Unternehmensnetzwerk | Business network | Prognoseverfahren | Forecasting model | Graphentheorie | Graph theory | Netzwerk | Network | Interbankenmarkt | Interbank market | Geldmarkt | Money market |
Saved in:
freely available
Saved in favorites
Similar items by subject
-
Mazzarisi, P., (2020)
-
A network approach to interbank contagion risk in South Africa
Mananga, Pierre Nkou, (2025)
-
Dynamic visualization of large transaction networks : the daily Dutch overnight money market
Heijmans, Ronald, (2014)
- More ...