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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Haojie, Laxman, Arjun, Yuan, Yichao, Flautner, Krisztian, Talati, Nishil
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910127823519744
author Ye, Haojie
Laxman, Arjun
Yuan, Yichao
Flautner, Krisztian
Talati, Nishil
author_facet Ye, Haojie
Laxman, Arjun
Yuan, Yichao
Flautner, Krisztian
Talati, Nishil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12241
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BlazingAML: High-Throughput Anti-Money Laundering (AML) via Multi-Stage Graph Mining
Ye, Haojie
Laxman, Arjun
Yuan, Yichao
Flautner, Krisztian
Talati, Nishil
Distributed, Parallel, and Cluster Computing
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.
title BlazingAML: High-Throughput Anti-Money Laundering (AML) via Multi-Stage Graph Mining
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2604.12241