-

Ant International Open Sources Time-Series Transformer AI Model to Enable More Businesses to Benefit from AI-Powered Forecasting

Ant International currently deploys the Falcon TST AI Model to forecast cashflow and FX exposure with more than 90% accuracy

SINGAPORE--(BUSINESS WIRE)--Ant International, a leading global digital payment, digitisation, and financial technology provider, has released its proprietary Falcon TST (Time-Series Transformer) AI model, the industry-first Mixture of Experts architecture-based big data model with multiple patch tokenizers, supported by up to 2.5 billion parameters. The model has also achieved state-of-the-art zero-shot results on well-acknowledged long-term forecasting benchmarks, such as absolute mean error rates.

Deployed internally at Ant International to manage cashflow and FX exposure on an hourly, daily and weekly basis, Falcon TST has achieved accuracy rates of over 90%, and cut the company’s FX costs by up to 60%.

Ant International also collaborated with various industry partners to deploy the model in different use cases, such as in helping businesses mitigate FX cost and volatility, as well as to support airlines in offering more stable, competitive pricing to their customers. With the Airports Council International World’s report estimating that global air travel is expected to reach almost 10 billion passengers in 20251, these applications of AI have the potential to translate to significant cost savings for consumers globally.

Extending the impact of AI-powered forecasting across industries

The model also enables businesses to make various other time-series forecasts, such as weather patterns, calendar events, financial market fluctuations, cross-border traffic data, and more.

“By open-sourcing our proven Falcon TST model, we aim to advance the field through global collaboration — inviting scientists worldwide to contribute real-world feedback and accelerate innovation in time series learning,” said Jiang-Ming Yang, Chief Innovation Officer, Ant International.

The Falcon TST AI Model is now available on GitHub and Hugging Face. Ant International invites interested developers to find out more about the model and recent success stories here:

https://falcon-tst.ant-intl.com

About Ant International

With headquarters in Singapore and main operations across Asia, Europe, the Middle East and Latin America, Ant International is a leading global digital payment, digitisation and financial technology provider. Through collaboration across the private and public sectors, our unified techfin platform supports financial institutions and merchants of all sizes to achieve inclusive growth through a comprehensive range of cutting-edge digital payment and financial services solutions. To learn more, please visit https://www.ant-intl.com/

1 GLOBAL AIR TRAVEL FORECASTED TO REACH 9.8 BILLION PASSENGERS IN 2025, NEARING THE HISTORIC 10 BILLION MILESTONE, 30 Sep 2025, Airports Council International World

Contacts

For media enquiries, please contact
Ant International Global Communications
pr@ant-intl.com

Ant International


Release Summary
Ant International has released its proprietary Falcon TST (Time-Series Transformer) AI model, a Mixture of Experts architecture-based big data model.
Release Versions

Contacts

For media enquiries, please contact
Ant International Global Communications
pr@ant-intl.com

More News From Ant International

Ant Group Open-Sources SingGuard-NSFA to Establish New Security Paradigms for Autonomous AI Agents

HANGZHOU, China--(BUSINESS WIRE)--Ant Group’s AI Security Lab today announced the open-source release of SingGuard-NSFA, a specialized security guardrail framework designed specifically for autonomous AI agents. The framework secures agentic AI systems against operational threats like prompt injection, addressing critical vulnerabilities as AI transitions from passive content generation to active, autonomous execution. As AI agents rapidly move from research labs to business scenarios, the secu...

Robbyant Launches LingBot-VA 2.0 Built Natively for Embodied AI and Physical World Control

SHANGHAI--(BUSINESS WIRE)--Robbyant, an embodied AI company within Ant Group, today announced the release of LingBot-VA 2.0, the industry’s first embodied-native video-action world model. This release marks a key transition in robotics foundation models, shifting from repurposing digital world models to designing them natively for the physical world. Instead of relying on fine-tuned digital content generation models, LingBot-VA 2.0 is built from scratch to meet the original demands of dynamic m...

Robbyant Unveils LingBot-World 2.0: Pioneering Hour-Long Real-Time Generation in World Models

SHANGHAI--(BUSINESS WIRE)--Robbyant, an embodied AI company within Ant Group, today announced the open-source release of LingBot-World 2.0 (Infinity). This interactive world model significantly upgraded its world prediction and interactivity capabilities, supporting hour-long continuous generation, 720p/60fps high-definition real-time output, and richer interactive actions. LingBot-World 2.0 also integrates a native agent mechanism, evolving generated worlds from merely watchable and controllab...
Back to Newsroom