Search Results
Working Paper
Can LLMs Improve Sanctions Screening in the Financial System? Evidence from a Fuzzy Matching Assessment
We examined the performance of four families of large language models (LLMs) and a variety of common fuzzy matching algorithms in assessing the similarity of names and addresses in a sanctions screening context. On average, across a range of realistic matching thresholds, the LLMs in our study reduced sanctions screening false positives by 92 percent and increased detection rates by 11 percent relative to the best-performing fuzzy matching baseline. Smaller, less computationally intensive models from the same language model families performed comparably, which may support scaling. In terms of ...
Working Paper
CardSim: A Bayesian Simulator for Payment Card Fraud Detection Research
Payment fraud has been high in recent years, and as criminals gain access to capability-enhancing generative AI tools, there is a growing need for innovative fraud detection research. However, the pace, diversity, and reproducibility of such research are inhibited by the dearth of publicly available payment transaction data. A few payment simulation methodologies have been developed to help narrow the payment transaction data gap without compromising important data privacy and security expectations. While these simulation approaches have enabled research advancements, more work is needed to ...
Discussion Paper
Monitoring AI Adoption in the U.S. Economy
This note uses three publicly available surveys with complementary target respondents to examine trends in AI adoption in the U.S. through 2025. Business survey data from the Census Bureau show that about 18 percent of firms have adopted AI as of year-end 2025.
Discussion Paper
The AI Buildout and the Economy: Publicly Available Data to Assess AI's Impact
This note presents publicly available indicators that can help researchers and policymakers track the evolution of the generative AI buildout and its potential impact on the economy on a timely basis. We organize the indicators into three categories: capabilities and costs; firm investment and adoption; and productivity and labor.
Discussion Paper
Governance of Permissionless Blockchain Networks
A permissionless blockchain network is a system of physically distributed computers running a copy of a shared ledger and using the same software rules that enable all network participants to “read, submit, and validate transactions” (Beck, Müller-Bloch, and King, 2018, p. 1022). A permissionless system’s accessibility stands in contrast to that of permissioned systems, in which a central authority pre-selects validators and potentially restricts viewing and submission rights (Krause, Natarajan, and Gradstein, 2017; Beck, Müller-Bloch, and King, 2018).