Ant International, a Singapore- and Shanghai-based payments and fintech company, said on August 20 that it introduced FalconTST 2.0, an updated time-series transformer AI model.

The model is designed to forecast foreign exchange risk and cash flow needs in cross-border payments.

The company said the model achieved a Mean Absolute Scaled Error score of 0.666 on a public evaluation benchmark.

It also reported forecast accuracy of more than 93%, although the press release did not identify the benchmark.

Ant International also said Barclays, Citi, Deutsche Bank, and Standard Chartered had integrated FalconTST 2.0 into tools for cash flow forecasting and foreign exchange liquidity or hedging management.

The company said the model was already used for foreign exchange and liquidity management in aviation and was expanding into ecommerce, logistics, and other industries.

It also invited developers to join an application programming interface trial on GitHub.

Publicly available material reviewed for this report did not provide enough detail to verify the benchmark used for FalconTST 2.0 or the extent of the banks’ deployments.

🔗 Source: Ant International

Recent Ant International developments