"Synthetic ISO 20022 pacs.008 and pacs.009 Payment Message Dataset for Fraud Detection and Machine Learning"

Read full text
Authors: Senthilnathan Dhanasekaran
Cited by: 0

Abstract

"This dataset provides fully synthetic ISO 20022 pacs.008 and pacs.009 payment messages generated for fraud detection and machine learning research. The messages are schema-valid and constructed using a constraint-aware, schema-driven process that preserves key behavioral characteristics such as amount distributions, temporal proximity, and inter-message consistency, while containing no real customer, account, or transaction data. The dataset is intended to support privacy-preserving experimentation in payment analytics, financial crime detection, and ISO 20022 system testing, and may be safely shared across institutions for research and development purposes."

Fields of Study & Subjects

Imbalanced Data Classification Techniques Privacy-Preserving Technologies in Data Cybercrime and Law Enforcement Studies

Publication details

Journal / source
IEEE DataPort
Publication date
10 January 2026
Document type
Dataset