# Ant International reports fraud model cut card losses 38% against XGBoost

Ant International says its 7-billion-parameter payment model, which reads transaction histories, transaction details and links between accounts together, cut fraud losses by about 38% in a four-month live test. The report is a preprint from the company itself, and nothing has been released for others to check.

- Category: In industry
- Readiness level: II (Benchmarked) on Science Underway's four-step scale, as proposed
- Published: 2026-11-20
- Editor: Stefan Perdal
- URL: https://scienceunderway.com/articles/ant-international-reports-fraud-model-cut-card-losses-38-against-xgboost

## The study

Antom 3-in-1 Transformer: A Payment Foundation Model (preprint, not peer reviewed). arXiv 2611.25403. https://arxiv.org/abs/2611.25403

## At a glance

- What it shows: Ant International built one large AI model to spot risky card payments. The model looks at a customer's past behaviour, the details of the current payment and the customer's links to other accounts. In a live test on part of its traffic, the company reports losses about 38% lower than with its older system.
- What it does not show: It does not show that the gain would hold at another payment company or with other kinds of fraud. Outsiders cannot check the result, because the company has not released code, model weights, data or full design details.
- Why it matters: Card fraud teams mostly use separate, smaller models for each signal. This is one of the first detailed reports of a single large model combining them in a live payment system, with a real business outcome measured.

## What the study shows

Ant International, which runs the Antom merchant payment platform, describes a fraud-detection model it calls Antom 3-in-1 Transformer. It has about 7 billion parameters, the adjustable numbers a model learns. Only about 1.7 billion are used for any one task. The paper is a preprint and has not been peer reviewed.

The model combines three kinds of input. The first is the history of recent payments for the user, the card and the device. The second is a table of facts about the current payment, such as amount and merchant. The third is a graph, a map of which users are connected to which. Each input has its own component, and a final stage blends them for each prediction task.

The model is first pretrained, meaning it learns general patterns from large amounts of unlabelled payment data. It is then fine-tuned on labelled fraud cases for each business. A label here is a confirmed record of whether a payment turned out to be fraud.

The authors report a live test from June to October 2026 on 30% of platform traffic. Payments were randomly split between the new model and two existing systems. One was XGB-Online, a gradient-boosted tree model, a common type of fraud model built from many small decision trees. The other was a neural model in the style of SAINT, a published method for table data. All three worked under the same rules and could act on the riskiest 0.5% of payments.

Against XGB-Online, the authors report that the new model cut the chargeback rate by 37.74% and the overall loss rate by 37.88%. A chargeback is when a payment is reversed after a dispute, often because of fraud. Against the SAINT-style model, the loss rate fell by about a quarter.

In the first stage of the test, the models scored payments without acting on them. Among the 0.5% of payments each model ranked riskiest, the new model caught about 30% of the risky transactions. XGB-Online caught about 7% and the SAINT-style model about 17%.

Offline, the authors also report that pretraining cuts the number of labels needed. On two merchant groups, the pretrained model trained with a quarter of the labels beat the same design trained from scratch with all of them. On IBM's public but synthetic credit-card dataset, it ranked fraud better than five published transaction models, though not on every measure.

## Our reading

This is a deployment report, not a recipe. It gives live business outcomes from a randomised test, which is rarer and more useful than another offline benchmark score. It also gives latency: the model answers in under 47 milliseconds on average on a single NVIDIA A10 graphics card, well inside the company's time budget for a card payment.

A concrete way to read the main result: suppose a platform can block or review 1 in 200 payments. In the authors' test, the older tree model's top picks would have caught about 7 in every 100 risky payments. The new model's picks would have caught about 30. That is the kind of gap that shows up in a loss line.

On our Readiness Scale we rate the work at level II, benchmarked. There are results on public datasets, but no released code or weights for level III. The production use is claimed by the developer itself, without independent confirmation, so we do not yet treat it as proven in production at level IV.

The rest of the article (what it means, limits, what to watch) is free for members: https://scienceunderway.com/articles/ant-international-reports-fraud-model-cut-card-losses-38-against-xgboost

## How this was made

An AI model read the study and wrote this article in the structure Science Underway uses. An editor reviewed it and approved it for publication. Check the original study before you rely on the details.

---
Source: Science Underway, https://scienceunderway.com/. Please link to the article when you cite it.
