Researchers from the Bank for International Settlements have used AI to produce daily forecasts of market dysfunction 60 business days before thy actually happen.
Editorial
This content has been selected, created and edited by the Finextra editorial team based upon its relevance and interest to our community.
Predicting financial market stress has long proven to be a largely elusive goal. But, AI’s ability to handle large datasets and unearth hidden nonlinear patterns has provided some hope that this could change.
For a working paper, BIS researchers built a two-step tool that forecasts market stress and explains the reasons behind its forecast. First, a recurrent neural network (RNN) learns from over one hundred daily market indicators. It predicts the average size of gaps between euro-yen traded directly and euro-dollar-yen traded via the US dollar.
These “triangular arbitrage parity” gaps should vanish within seconds in normal times, and big or persistent gaps signal that market frictions are rising.
Second, the model shows, day by day, which market indicators matter most for its signal. This information can then direct a large language model to search recent news about those high-importance indicators to add timely context.
The system flags periods of likely dysfunction up to 60 business days ahead, say the researchers. In tests on data not used for training from 2021-24, it correctly highlights episodes later linked to real events, including the March 2023 banking strains.
When the model raises an alert, its highest-weight indicators guide targeted news searches. In case studies, those searches pointed to discussions of the relevant drivers days before turbulence.
The team concludes: “In short, the tool detects risk early and explains it in accessible terms, helping authorities focus their surveillance and prepare responses.”
Read the paper:
Download the document now 2.1 mb (Chrome HTML Document)