Ant International launched an upgraded version of its artificial intelligence model on Thursday (August 20), signing up major global banks as financial institutions accelerate the adoption of specialised AI to manage liquidity risks.
The Singapore-based fintech giant rolled out its Falcon Time-Series Transformer (TST) AI Model 2.0 and has partnered with six large banks, including Citi, HSBC, Deutsche Bank, Standard Chartered and Barclays, according to Kelvin Li, the firm’s general manager of platform tech.
The launch comes amid an accelerating global race among financial institutions to embed AI into their core operations.
The Group described the model as its most advanced tool so far, designed to deliver more accurate forecasting in real-world FX risk management for cross-border payments. In the coming months, Ant Group will also introduce more cutting-edge industry applications, including demand forecasting for supply chain management in e-commerce platforms and predictive operations management for the aviation industry.
“FalconTST 2.0 shows excellent performance on the Mean Absolute Scaled Error (MASE) metric in a leading global evaluation for time-series models. MASE is among the most critical metrics used to evaluate time-series models. FalconTST 2.0 achieved an MASE score of 0.666 and places it at the top of the leaderboard, surpassing other TST foundational models from leading global tech companies,” the venture remarked.
While large language models are excellent at understanding text, TST models have become essential in finance and payments because they can quickly adapt to changes in liquidity needs, foreign-exchange rates, and transaction flows. The financial information consists of continuously changing numerical data — transaction amounts, account balances, settlement flows, and currency positions.
“For a global payment institution, these forecasts directly impact capital efficiency. The value of AI prediction lies not just in calculating more accurately but in helping businesses know precisely when they need funds, how much they need, and in which currencies,” Li 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,” he added further.
“This forecasting capability is equally critical for foreign exchange management. An airline may collect ticket revenues in multiple currencies while needing to pay for aircraft leases, airport fees, and operating expenses in different currencies. Companies typically use foreign exchange hedging to reduce currency fluctuation risk, but that requires them to determine how much of each currency they will receive and need. If forecasts are too high, they may over-hedge; if too low, they leave themselves exposed to foreign exchange risk,” the senior official added further.
Traditional forecasting systems typically build separate models for different tasks. For example, a retail company trains a sales forecast model, an aviation venture a demand forecast model, and a financial institution a liquidity model. TST foundational models, on the other hand, take a different approach, as FalconTST learns common patterns — cycles, trends, seasonality, and sudden shifts — from data across finance, retail, energy, travel, and economics. Though these industries differ, the underlying temporal structures often share commonalities.
While Barclays has integrated the FalconTST Model into its FX hedging platform, BARX NetFX, Citi combined FalconTST with their own Fixed FX Rates solution. They are mainly used for FX risk management on e-commerce platforms or airlines. Standard Chartered uses the model alongside its SCALE FX system as part of both sides’ participation in the PathFin.ai programme of the Monetary Authority of Singapore (MAS).
“Currently, they all have adopted the 2.0 version of the FalconTST Model, leading to an improved forecasting accuracy of more than 93% consistently. This level of precision is critical for financial institutions managing vast volumes of cross-border payments and needing to mitigate currency fluctuation risks effectively,” Li noted.
Ant International said another goal of FalconTST is to make the same forecasting capability reusable across customers and industries. Aviation is a typical use case: revenues and costs span multiple currencies, while cash flows can change rapidly, making accurate forecasting critical. The sector is already using FalconTST for FX and liquidity management, and it is expanding into e-commerce, logistics, and other industries.
If a capability serves only one customer, it remains largely a customised solution. When it can be reused across customers and industries, it starts to become a foundational capability.
“Large language models have shown how AI can understand and generate information. FalconTST is about another capability that businesses increasingly need: understanding how the world changes over time and anticipating what comes next. For us, the value of AI is not simply achieving a better forecasting score but turning that predictive intelligence into real decisions—how much liquidity to prepare, how to manage FX exposure, and how to allocate capital more efficiently. FalconTST 2.0 is an important step toward making predictive AI a foundational capability for global businesses across payments, accounts and broader financial services,” said Jiang-Ming Yang, the Group’s Chief Innovation Officer.