Ant International has launched an upgraded Falcon Time Series Transformer model, delivering faster, more accurate foreign-exchange predictions to optimise cross-border payments and minimise currency risk for multinational firms.
Ant International has rolled out an upgraded version of its Falcon Time Series Transformer model, aiming to sharpen foreign-exchange forecasting for cross-border payments and help firms manage currency risk more efficiently. The company says the system is built for fast-moving numerical data such as transaction volumes, account balances, settlement flows and currency positions, rather than the language-style tasks handled by large language models. In practical terms, Ant argues, better prediction can improve capital use by showing businesses when cash will be needed, how much will be required and in which currencies.
The firm says the model is designed around patterns that recur across time-series data, including trends, cycles, seasonality and sudden shifts. That approach differs from traditional forecasting systems that often rely on separate models for different jobs. Ant says Falcon TST draws on data from sectors such as finance, retail, energy, travel and economics, on the basis that many of the underlying movements are similar even when the industries are not.
Several major banks have already adopted Falcon TST 2.0, according to Ant International and reports from technology and banking publications. Barclays has integrated the model into its BARX NetFX hedging platform, while Citi is combining it with its fixed FX rates solution. Standard Chartered is using it alongside its Scale FX system as part of the PathFin.ai programme run with the Monetary Authority of Singapore. Deutsche Bank is also among the users cited by Ant and in related reporting.
Jiang-Ming Yang, Ant International’s chief innovation officer, said the value of the technology lies in turning forecasting into operational decisions, including liquidity planning, FX exposure management and capital allocation. The company claims the system is especially useful for businesses with revenues and costs spread across multiple currencies, such as airlines, where getting the hedge size wrong can either leave exposures uncovered or create unnecessary over-hedging. Some reports have said the model has achieved strong benchmark results and may cut hedging and allocation costs materially, though those figures come from company-linked claims and should be treated cautiously.
Disclaimer: This article is intended to inform and educate, not to recommend or endorse any financial product, investment or strategy. Please consider your own financial circumstances and seek professional advice where appropriate before making financial decisions.
