# DeepTrax: Embedding Graphs of Financial Transactions

arXiv: https://arxiv.org/abs/1907.07225 · HTML: https://mlsanity.com/paper/1907.07225/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2019.

## Built on by (most cited first, 15 of 15)

- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [Contrastive Pre-training for Imbalanced Corporate Credit Ratings](https://mlsanity.com/paper/2102.12580/) (2021)
- [Dynamic Customer Embeddings for Financial Service Applications](https://mlsanity.com/paper/2106.11880/) (2021)
- [DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning](https://mlsanity.com/paper/2407.18523/) (2024)
- [Adversarial Semi-supervised Learning for Corporate Credit Ratings](https://mlsanity.com/paper/2104.02479/) (2021)
- [Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users](https://mlsanity.com/paper/2204.11849/) (2022)
- [PG2Net: Personalized and Group Preferences Guided Network for Next Place Prediction](https://mlsanity.com/paper/2110.08266/) (2021)
- [GRAPHYP: A Scientific Knowledge Graph with Manifold Subnetworks of Communities. Detection of Scholarly Disputes in Adversarial Information Routes](https://mlsanity.com/paper/2205.01331/) (2022)
- [Are Graph Representation Learning Methods Robust to Graph Sparsity and Asymmetric Node Information?](https://mlsanity.com/paper/2205.09648/) (2022)
- [Transaction Fraud Detection via an Adaptive Graph Neural Network](https://mlsanity.com/paper/2307.05633/) (2023)
- [MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings](https://mlsanity.com/paper/2411.00287/) (2024)
- [Specialized text classification: an approach to classifying Open Banking transactions](https://mlsanity.com/paper/2504.12319/) (2025)
- [Unnoticeable Community Deception via Multi-objective Optimization](https://mlsanity.com/paper/2509.01438/) (2025)
- [Representation Learning on Large Non-Bipartite Transaction Networks using GraphSAGE](https://mlsanity.com/paper/2509.12255/) (2025)

## Abstract (arXiv)

Financial transactions can be considered edges in a heterogeneous graph between entities sending money and entities receiving money. For financial institutions, such a graph is likely large (with millions or billions of edges) while also sparsely connected. It becomes challenging to apply machine learning to such large and sparse graphs. Graph representation learning seeks to embed the nodes of a graph into a Euclidean vector space such that graph topological properties are preserved after the transformation. In this paper, we present a novel application of representation learning to bipartite graphs of credit card transactions in order to learn embeddings of account and merchant entities. Our framework is inspired by popular approaches in graph embeddings and is trained on two internal transaction datasets. This approach yields highly effective embeddings, as quantified by link prediction AUC and F1 score. Further, the resulting entity vectors retain intuitive semantic similarity that is explored through visualizations and other qualitative analyses. Finally, we show how these embeddings can be used as features in downstream machine learning business applications such as fraud detection.