国际清算银行-利用人工智能监控金融市场（英）

BIS Working Papers No 1291 Harnessing artificial intelligence for monitoring financial markets by Matteo Aquilina, Douglas Araujo, Gaston Gelos, Taejin Park and Fernando Pérez-Cruz Monetary and Economic Department September 2025 JEL classification: G14, G15, G17 Keywords: Market dysfunction, liquidity, arbitrage, artificial intelligence, financial stability BIS Working Papers are written by members of the Monetary and Economic Department of the Bank for International Settlements, and from time to time by other economists, and are published by the Bank. The papers are on subjects of topical interest and are technical in character. The views expressed in them are those of their authors and not necessarily the views of the BIS. This publication is available on the BIS website (www.bis.org). © Bank for International Settlements 2025. All rights reserved. Brief excerpts may be reproduced or translated provided the source is stated. ISSN 1020-0959 (print) ISSN 1682-7678 (online) Harnessing artificial intelligence for monitoring financial markets 1 Harnessing artificial intelligence for monitoring financial markets1 Matteo Aquilina1,2, Douglas Araujo3, Gaston Gelos1,4, Taejin Park1 Fernando Pérez-Cruz1 1 Bank for International Settlements 2 Macquarie University 3 Central Bank of Brazil 4 CEPR Abstract Predicting financial market stress has long proven to be a largely elusive goal. Advances in artificial intelligence and machine learning offer new possibilities to tackle this problem, given their ability to handle large datasets and unearth hidden nonlinear patterns. In this paper, we develop a new approach based on a combination of a recurrent neural network (RNN) and a large language model. Focusing on deviations from triangular arbitrage parity (TAP) in the Euro-Yen currency pair, our RNN produces interpretable daily forecasts of market dysfunction 60 business days ahead. To address the “black box” limitations of RNNs, our model assigns data-driven, time-varying weights to the input variables, making its decision process transparent. These weights serve a dual purpose. First, their evolution in and of itself provides early signals of latent changes in market dynamics. Second, when the network forecasts a higher probability of market dysfunction, these variable-specific weights help identify relevant market variables that we use to prompt an LLM to search for relevant information about potential market stress drivers. Keywords: Market dysfunction, liquidity, arbitrage, artificial intelligence, financial stability JEL classification: G14, G15, G17 1 We are grateful for the useful discussions with Tomaso Aste and team, Salih Gönüllü, Alan Moreira, and for comments received from seminar participants at the Journal of Banking and Finance paper development workshops on “Generative AI in Finance” in Dresden and in Montreal (2024), the central bank participants at the Consultative Group of Directors of Fin