DeepTrax: Embedding Graphs of Financial Transactions
They consider the Bipartite network of credit card transactions (between account holders and merchants), but in the end, it uses the sentences that are made of merchants that are grouped by a fixed time period.
an edge between two merchant vertices represents the presence of at least one account who made transactions at both merchants within a specified time window.
Cites
- Baldassini2018client2vec: client2vec: Towards Systematic Baselines for Banking Applications
Cited by
- Cheng2020contagious - Contagious Chain Risk Rating for Networked-guarantee Loans
- Gogoglou2020navigating - Navigating the dynamics of financial embeddings over time
- https://arxiv.org/abs/2001.08427 - Linking Bank Clients using Graph Neural Networks Powered by Rich Transactional Data
- https://arxiv.org/abs/1910.03081 - On the Interpretability and Evaluation of Graph Representation Learning
- https://arxiv.org/abs/2009.14588 - EWS-GCN: Edge Weight-Shared Graph Convolutional Network for Transactional Banking Data
- https://arxiv.org/abs/2006.10252 - Quantifying Challenges in the Application of Graph Representation Learning