Superpower Daily
Ant Puts Its FX Forecasting Model Into Tools Used by Major BanksAWS Brings GPT-5.6 Cross-Region Inference, With a Data-Location...Palo Alto and NTT DATA Build a $1B Security Alliance Without Ex...Cursor Gives Cloud Agents a Way to Come Back to the JobArmy Cyber Puts AI Agents on Network Duty but Keeps Risk Decisi...Databricks Pushes Feature Stores From Batch Lag to 200ms Freshn...Ant Puts Its FX Forecasting Model Into Tools Used by Major BanksAWS Brings GPT-5.6 Cross-Region Inference, With a Data-Location...Palo Alto and NTT DATA Build a $1B Security Alliance Without Ex...Cursor Gives Cloud Agents a Way to Come Back to the JobArmy Cyber Puts AI Agents on Network Duty but Keeps Risk Decisi...Databricks Pushes Feature Stores From Batch Lag to 200ms Freshn...
Modelspublished

Ant Puts Its FX Forecasting Model Into Tools Used by Major Banks

The model targets a specific treasury problem in cross-border payments: predicting the timing, size and currency of cash needs. Its reported bank integrations are meaningful, but their scale—and one headline accuracy measure—remain unclear.

By 3 min read
Ant Puts Its FX Forecasting Model Into Tools Used by Major Banks
Sign in to save and react

Listen to this story

The audio brief

About 1:38
0:001:38
Read transcript
Ant International says its FalconTST 2.0 forecasting model is now inside treasury tools used by Barclays, Citi, Deutsche Bank and Standard Chartered. The practical job is narrow but important: helping banks predict when cross-border payments will require cash, how much they will need, and in which currencies. Ant announced the model on August 19 as a time-series system for constantly changing financial data—transactions, account balances, settlement flows and currency positions. That makes it different from a general-purpose chatbot. Its forecasts are being applied to cash-flow planning, foreign-exchange liquidity, and hedging management: decisions about funding payment flows and managing currency exposure. Ant says six major banks have signed partnerships involving the model. Besides the four named users, that list includes HSBC, with one partner not identified. But the announcement does not say how broadly each bank has deployed it, or whether the model is used beyond the specified treasury functions. The clearest reported performance figure is a 0.666 Mean Absolute Scaled Error score on a public benchmark. Ant also claims accuracy above 93 percent, but it has not identified the benchmark behind that number, so the two figures cannot be cleanly compared. The next test is expansion. Ant says the model is already used in aviation, plans applications for e-commerce supply chains and aviation operations, and is opening an API trial through GitHub. The question is whether those experiments—and the bank partnerships—turn a targeted treasury tool into a broader forecasting platform.

Story brief

3 key points

FalconTST 2.0 is moving from demonstration to targeted financial workflows: Ant International says four named banks are using it for treasury forecasting, FX liquidity, or hedging, while six banks have signed partnerships. Ant reports a 0.666 Mean Absolute Scaled Error on a public benchmark and accuracy above 93%, but does not identify the latter benchmark. The practical question is whether deployments broaden...

  1. 01

    Ant announced FalconTST 2.0 on August 19 for sequence data such as transactions, balances, settlements and currency positions.

  2. 02

    Named deployments are at Barclays, Citi, Deutsche Bank and Standard Chartered; HSBC is among the six partnership signatories.

  3. 03

    Ant’s 0.666 benchmark score is more comparable than its separate “above 93%” accuracy claim, whose benchmark is undisclosed.

Ant International says its FalconTST 2.0 forecasting model is now being used in tools at Barclays, Citi, Deutsche Bank and Standard Chartered for cash-flow forecasting and foreign-exchange liquidity or hedging management. The deployment puts AI into decisions over how much cash to prepare for cross-border payments and which currencies to hold.

The company announced Falcon Time-Series Transformer 2.0 on August 19. It is built to forecast foreign-exchange risk and cash-flow needs for financial institutions, rather than to handle the broad text tasks associated with general-purpose chatbots.

The model’s job is to turn moving payment data into cash decisions

Ant describes the relevant information as numbers that keep changing: transaction amounts, account balances, settlement flows and currency positions. A time-series model is designed for that kind of sequence data, where the recent path of values is part of the forecast.

Ant says the useful output is not simply a better score. The forecast is meant to help a business determine when it needs funds, how much it needs and in which currencies—inputs to preparing liquidity and managing FX exposure.

What Ant says the bank tools cover

  • Cash-flow forecasting, which estimates future funding needs.
  • Foreign-exchange liquidity management, which concerns currency funds available for payment flows.
  • Foreign-exchange hedging management, which Ant includes among the model’s named bank uses.
Ant’s disclosed benchmark result
0.666Mean Absolute Scaled Error

Ant International said FalconTST 2.0 achieved a 0.666 Mean Absolute Scaled Error score on a public evaluation benchmark.

The customer list is larger than the named deployments

Ant says six major banks have signed partnerships involving FalconTST 2.0. It named Citi, HSBC, Deutsche Bank, Standard Chartered and Barclays, leaving one partner unnamed. The company separately says Barclays, Citi, Deutsche Bank and Standard Chartered are using the model.

The public description identifies the functions receiving the model, not the breadth of each bank’s use. Ant also reported forecast accuracy above 93%, but did not identify the benchmark behind that figure. Those two limits make the announcement evidence of specific integrations, not a measure of enterprise-wide adoption or a fully comparable performance claim.

Ant is testing the same capability outside banking

Ant says FalconTST 2.0 was already being used for foreign-exchange and liquidity management in aviation. It plans to extend the model to e-commerce supply-chain demand forecasting and predictive operations management for aviation, applying the same kind of forecasting to different streams of business data.

The company has also invited developers to an API trial through GitHub. That opens a route for outside developers to test applications beyond Ant’s initial partners, while the bank announcement remains centered on treasury-related tools.

The next concrete test is whether named banks expand FalconTST 2.0 beyond the cash-flow, liquidity and hedging tools Ant has described.

Sources

  1. pymnts.comAnt International Recruits Banking Giants for Updated AI Model | PYMNTS.com
  2. finance.biggo.comAnt International Launches Specialized AI Model, Signs Citi, HSBC and Four Other Global Banks — BigGo Finance

Related coverage

Continue reading