Ant International FalconTST 2.0 AI Boosts FX Hedging for Barclays, Citi, Deutsche Bank, Standard Chartered
Ant International's FalconTST 2.0 artificial intelligence model now powers foreign exchange forecasting for four global banks. The system aims to improve cross-border payment risk management.
Global Banks Adopt AI for FX Forecasting
Ant International has deployed its Falcon Time-Series Transformer (TST) AI Model 2.0, now powering foreign exchange (FX) forecasting for four major global banks. Barclays, Citi, Deutsche Bank, and Standard Chartered are integrating the system to enhance FX risk management in cross-border payments.
This advanced model aims to deliver more accurate predictions, a critical capability for international financial operations. Ant International initially used FalconTST 1.0 internally to manage its own cash flow and FX exposure across hourly, daily, and weekly cycles.
Advanced AI Model Surpasses Benchmarks
The FalconTST 2.0 model demonstrates State-of-the-Art (SOTA) performance, according to Ant International. It achieved a 0.666 Mean Absolute Scaled Error (MASE) score, a key metric for evaluating time-series models. This performance reportedly surpasses other foundational TST models from leading global technology companies.
The model's strength lies in learning common patterns, such as cycles, trends, sudden shifts, and seasonality, from diverse datasets including finance, energy, and retail. Traditional forecasting systems typically build separate models for each task.
Operational Value and Cost Savings
Jiang-Ming Yang, Ant International's Chief Innovation Officer, highlighted the model's strategic value. He explained that FalconTST helps businesses understand how the world changes over time and anticipate future developments.
Kelvin Li, General Manager of Platform Tech and Senior Vice President at Ant International, added that the system assists global businesses, including Ant International itself, in managing complex cash flow and FX exposure. Clients using FalconTST 1.0 previously reported "real operational value and cost savings" from improved forecasting, Li noted.
The adoption of FalconTST 2.0 by major banks indicates a broader industry move towards AI-driven FX hedging. For Asian economies and businesses, this technology can significantly streamline cross-border transactions and reduce currency volatility risks. Improved forecasting leads to better cash flow management and more efficient FX liquidity.
This can protect profit margins for companies engaged in international trade and investment, fostering greater confidence in managing global financial flows. Future applications may include demand forecasting for e-commerce supply chains and predictive operations for aviation.
This article is journalism, not investment advice; consult a licensed professional before making financial decisions. Market data is indicative, may be delayed, and should be verified with your broker or exchange before use.
Comments.
Comments are moderated. We remove what is unlawful, abusive or off-topic, and and you remain responsible for what you post.
Reader comments open soon. Until then, corrections and responses go to our newsroom, and we publish what we get wrong on Corrections.