Ant International launches AI model for banking liquidity and currency hedging

Ant International has introduced Falcon TST 2.0, an advanced artificial intelligence model designed to predict cash flows, manage liquidity, and handle currency hedging. Unlike generative language models that process text, this time-series transformer model analyzes numerical data, including transaction amounts, account balances, and currency positions.

Major global financial institutions, including Citi, HSBC, Deutsche Bank, Standard Chartered, and Barclays, are collaborating with the Singapore-based fintech company to deploy the model. Ant International claims the technology can reduce costs related to currency hedging and fund allocation by more than 60 percent by providing more accurate forecasts of when and in which currencies funds will be required.

Beyond the banking sector, the company plans to expand the model's applications to include supply chain demand forecasting for e-commerce and predictive operational management within the aviation industry.