Barclays, Citi, Deutsche Bank, and Standard Chartered have implemented a new AI model to improve their foreign exchange forecasting and improve liquidity management.

Singapore-based tech company Ant International launched its Falcon Time-Series Transformer (TST) 2.0 model on Thursday saying it demonstrates state-of-the-art performance on the key Mean Absolute Scaled Error metric used to determine the accuracy of forecasting tools. The model aims to allow banks to more efficiently engage in foreign exchange hedging by predicting the amounts of different currencies an institution will receive and need over a given timeframe. Using the FalconTST 2.0 model, partner banks are able to forecast these figures with a more than 93 per cent accuracy, Ant International said.

The tool is being used in different ways by different banks. Barclays and Citi have integrated the AI model into their existing forex solutions, which are mainly used for risk management on e-commerce platforms or airlines.

Standard Chartered is using the model alongside its SCALE forex system as part of its participation in the Monetary Authority of Singapore’s PathFin.ai programme, of which Ant International is also a participant.

Rather than being trained on large, unstructured data sets like a large language model, FalconTST is trained on numerical data across finance, retail, energy, travel, and economics in order to learn common patterns that enhance its prediction capabilities.

FalconTST 2.0 ranked at the top of a global public benchmark of the metric, beating other TST foundational models from leading tech companies, Ant International added.

Kelvin Li, general manager of platform tech and senior vice president at Ant International said: “FalconTST helps global businesses, including our own, manage complex cash flow and FX exposure, so they can manage cross-border transactions with greater confidence.

“With FalconTST 1.0, clients saw real operational value and cost savings from better forecasting. With FalconTST 2.0, enhanced accuracy and precision let us extend those benefits to our banking partners as well as a broader range of customers across fast-moving sectors like e-commerce, travel and fintech.”

This adoption is the latest sign that AI use is increasing in the financial sector, and major model developers including Anthropic have launched models to capitalise on this appetite. However, its adoption is not uncontroversial: Ratings giant Moody’s warned earlier in August that increasing dependence on AI by big banks could leave them vulnerable to price hikes and outages in the future.

---