Reproduce “Leveraging Time-Series Foundation Models for Financial Crime Detection” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Danae Natalie Savvidi, H. Çağrı Bilgi, Kubilay Atasu, Arie van Deursen
The authors develop TCEE, which classifies suspicious transfers by letting each transaction retrieve context from the histories of its sender and receiver, rather than using one shared account summary. On six simulated AMLWorld datasets, TCEE-MLP beats the strongest evaluated baseline on five, with a 10.8% average relative PR-AUC gain, and is 6.0× faster end-to-end on average. Real-bank performance remains untested.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.