Anomaly Detection in Financial Transactions Via Graph-Based Feature Aggregations

Hewen Wang*, Renchi Yang, Jieming Shi

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Anomaly detection in the financial domain aims to detect abnormal transactions such as fraudulent transactions that can lead to loss of revenues to financial institutions. Existing solutions utilize solely transaction attributes as feature representations without the consideration of direct/indirect interactions between users and transactions, leading to limited accuracy. We formulate anomaly detection in financial transactions as the problem of edge classification in an edge-attributed multigraph, where each transaction is regarded as an edge, and each user is represented by a node. Then, we propose an effective solution DoubleFA, which contains two novel schemes: proximal feature aggregation and anomaly feature aggregation. The former is to aggregate features from neighborhoods into edges based on top-k Personalized PageRank (PPR). In anomaly feature aggregation, we employ a predict-and-aggregate strategy to accurately preserve anomaly information, thereby alleviating the over-smoothing issue incurred by proximal feature aggregation. Our experiments comparing DoubleFA against 10 baselines on real transaction datasets from PayPal demonstrate that DoubleFA consistently outperforms all baselines in terms of anomaly detection accuracy. In particular, on the full PayPal dataset with 160 million users and 470 million transactions, our method achieves a significant improvement of at least 23% in F1 score compared to the best competitors.

Original languageEnglish
Title of host publicationBig Data Analytics and Knowledge Discovery
Subtitle of host publication25th International Conference, DaWaK 2023, Penang, Malaysia, August 28–30, 2023, Proceedings
EditorsRobert Wrembel, Johann Gamper, Gabriele Kotsis, A Min Tjoa, Ismail Khalil
PublisherSpringer Cham
Pages64-79
Number of pages16
Edition1st
ISBN (Electronic)9783031398315
ISBN (Print)9783031398308
DOIs
Publication statusPublished - 9 Aug 2023
EventBig Data Analytics and Knowledge Discovery - 25th International Conference, DaWaK 2023 - Penang, Malaysia
Duration: 28 Aug 202330 Aug 2023
https://link.springer.com/book/10.1007/978-3-031-39831-5

Publication series

NameLecture Notes in Computer Science
Volume14148
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameDaWaK: International Conference on Big Data Analytics and Knowledge Discovery

Conference

ConferenceBig Data Analytics and Knowledge Discovery - 25th International Conference, DaWaK 2023
Country/TerritoryMalaysia
CityPenang
Period28/08/2330/08/23
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • Computer Science(all)

User-Defined Keywords

  • Anomaly Detection
  • Financial Transaction Network
  • Graph Embedding

Fingerprint

Dive into the research topics of 'Anomaly Detection in Financial Transactions Via Graph-Based Feature Aggregations'. Together they form a unique fingerprint.

Cite this