BlazingAML: High-Throughput Anti-Money Laundering (AML) via Multi-Stage Graph Mining

2026-04-13

AI Summary

This work addresses the challenges of anti-money laundering (AML) detection, particularly the high false positive rates and the difficulty of modeling multi-stage, complex laundering behaviors. Existing graph-based and AI-driven approaches struggle to effectively handle structural and temporal ambiguities inherent in such patterns. To overcome these limitations, the authors propose a multi-stage graph mining framework that captures ambiguous laundering behaviors through logical phase decomposition and graph operation chaining. They further introduce a domain-specific compiler that automatically translates high-level pattern specifications into highly optimized CPU/GPU code, eliminating the need for manual parallel programming. Evaluated on the IBM AML dataset, the approach achieves F1 scores comparable to state-of-the-art models while delivering speedups of 210× on CPU and 333× on GPU, significantly enhancing scalability and deployment efficiency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Money laundering detection faces challenges due to excessive false positives and inadequate adaptation to sophisticated multi-stage schemes that exploit modern financial networks. Graph analytics and AI are promising tools, but they struggle with the fuzziness of laundering patterns, which exhibit structural and temporal variations. Conventional data mining techniques require the detailed enumeration of pattern variants, which not only complicates the analyst's task to specify them, but also leads to large run-time overheads and difficulty training accurate AI models. The paper presents BlazingAML, a scalable AML system design that introduces: 1. A novel multi-stage framework for expressing fuzzy money laundering patterns 2. A domain-specific compiler that transforms high-level pattern descriptions into high-performance code for CPU and GPU back-ends The multi-stage abstraction decomposes complex laundering schemes into logical stages connected by graph operations, enabling diverse patterns to be expressed using unified primitives while capturing structural and temporal fuzziness. The compiler applies sophisticated optimizations, eliminating manual parallel programming requirements for financial analysts. Evaluation on IBM AML datasets shows BlazingAML achieves the same F1 score as state-of-the-art approaches while delivering 210x and 333x higher speedup on CPU and GPU respectively, with superior scalability.

Problem

• Anti-Money Laundering
• multi-stage schemes
• graph mining
• false positives
• pattern fuzziness

Innovation

• multi-stage graph mining
• domain-specific compiler
• fuzzy pattern representation
• high-throughput AML
• automated code generation