Antom 3-in-1 Transformer: A Payment Foundation Model

Weiyu Han, Haoyu Jiang, Jie Sheng, Youxi Pan, Xianglong Liu, Zeqi Ren, Dongquan Yi, Yinhao Liu, Ruobing Zuo, Ze Zhao, Huilin He, Nairong Zhang, Xinyi He, Xiao Tan, Jun Wang, Pan Fang, Wei Zeng, Jianan Su, Kaixin Shen, Jingtong Wu, Hao Li, Shuai Chen, Jiangming Yang, Tianyi ZhangarXiv 2026 · arXiv

TL;DR

Antom 3-in-1 Transformer is a 7-billion parameter foundation model designed by Ant International to revolutionize payment risk detection. By jointly modeling transaction sequences, tabular features, and graph-based entity relationships, it achieves a massive 37.88% reduction in fraud loss rates in real-world production environments while significantly lowering the amount of labeled data required for new business scenarios.

What Problem Does This Paper Address?

Detecting fraud in global payment systems is a high-stakes game of cat-and-mouse. Fraudsters constantly evolve their tactics, and data distributions vary wildly across different markets and merchant types. Traditionally, risk systems have relied on specialized, siloed models: one might look at a user's transaction history (sequence), another at the specific details of the current transaction (tabular), and a third at how accounts are linked (graph).

The challenge is twofold:

  1. Fragmentation: These separate perspectives often miss the "complete picture." An ordinary-looking transaction might be high-risk when viewed through the lens of its associated device network.
  2. Cold-Start & Label Scarcity: Training effective models for a new business or market requires a mountain of labeled data, which is often unavailable.

The authors propose a "foundation model" approach—pretraining a massive, multi-modal model on billions of transactions to learn universal patterns of behavior that can be easily adapted to specific tasks with minimal labels.

Methods

The Antom 3-in-1 Transformer uses a modular architecture to ingest three distinct data modalities:

  • Sequence Modality: Independent Transformer towers encode the histories of users, cards, and devices. It uses a novel Prefix-Future Contrast (PFC) pretraining objective, which forces the model to predict a statistical summary of future activity based on a historical prefix.
  • Tabular Modality: This captures the "here and now" of a transaction. It uses field tokenization and self-attention to model interactions between attributes like transaction amount, merchant category, and business statistics.
  • Graph Modality: A Graph Attention Network (GAT) processes "rolling user graphs" to capture relational risk (e.g., many accounts sharing one device).
  • Task-Conditioned Fusion: To manage the 7B parameters efficiently, the model uses a Sparse Mixture-of-Experts (MoE) approach. Only about 1.7B parameters are activated for any given task route. Task-specific "queries" guide how the sequence and tabular representations are fused before being augmented by graph embeddings.
Overview of the Antom 3-in-1 architecture showing the three modalities and the fusion block.

Datasets

The model was trained and evaluated on a mix of massive internal and public datasets:

  • Industrial Datasets: Billion-scale internal card-payment data from Ant International, including specific domains like Antom-Merchant A/B and AlipayHK.
  • IBM Synthetic Dataset: A standard benchmark containing ~24 million synthetic credit card transactions.
  • Public Graph Benchmarks: Amazon, YelpChi, T-Finance, and Elliptic (Bitcoin) were used to validate the graph encoder's performance.
  • Fusion Benchmarks: TransXion (AML benchmark) and the Multimodal Banking Dataset (MBD).

Key Insights and Ideas

  • The Power of Multi-modality: Sequence data provides the strongest standalone signal for risk, but the "3-in-1" integration is what drives peak performance. Removing any one modality significantly degrades results.
  • Label Efficiency is the Killer App: One of the most striking findings is that the pretrained model using only 25% of training labels outperforms a "from-scratch" baseline using 100% of labels. This drastically reduces the barrier to securing new payment scenarios.
  • Cross-Scenario Synergy: Richer transaction histories from one domain (e.g., a global e-marketplace) can actually help improve models for a completely different, label-scarce domain. Pretraining learns "reusable behavioral capabilities" that transcend specific merchant types.
  • Real-time Feasibility: Despite its size, the model fits into a strict 250ms end-to-end budget for real-time risk decisions. This is achieved by computing graph embeddings offline and using optimized GPU inference for the sequence and tabular encoders.
The online scoring timeline, showing how the model fits into the 250ms budget.

Key Results

The model's performance was validated through a four-month online A/B test on Ant International’s platform:

  • Loss Rate Reduction: Compared to the previous production model (XGB-Online), the Antom 3-in-1 Transformer reduced the overall loss rate by 37.88%.
  • Chargeback (CB) Rate: It reduced the pooled CB rate by 37.74%.
Table showing online portfolio results relative to XGB-Online.
  • Open-Source Benchmarking: On the IBM synthetic dataset, it achieved an Average Precision (AP) of 0.3829, outperforming the previous state-of-the-art (PRAGMA) by 12.2% and reaching a fraud recall of 83.22% at a 0.5% intervention budget.
Comparison of Antom 3-in-1 against other baselines on the IBM dataset.

Limitations and Future Work

The authors acknowledge several constraints:

  • Transparency: Due to competitive and safety considerations, specific details regarding the model architecture, training configurations, and exact dataset construction were omitted from this report.
  • Graph Latency: Currently, graph embeddings are computed offline and looked up at scoring time. Integrating dynamic, real-time graph updates into the 250ms inference window remains a challenge.
  • Scope: The report focuses on card-payment risk; extending this foundation model to other financial tasks like credit scoring or insurance fraud is a logical next step.

Summary updated

Abstract

We report the development of Antom 3-in-1 Transformer, a payment foundation model that integrates sequence, tabular, and graph representations for payment risk detection. The model contains approximately 7B parameters, with approximately 1.7B activated per task route. Antom 3-in-1 Transformer is pretrained to learn reusable behavioral and relational representations, primarily on Ant International's internal payment data. In a cross-business transfer experiment, pretraining improves the target business metric by 34.5% over the same architecture trained from scratch. With only 25% of the training labels, the pretrained model outperforms the full-label scratch baseline in Average Precision (AP) and [email protected]% on different merchant domains. In a four-month online experiment on Ant International's billion-scale payment platform, the model reduced the overall loss rate by 37.88% relative to XGB-Online.
BibTeX
@misc{han2026antom,
  author = {Weiyu Han and Haoyu Jiang and Jie Sheng and Youxi Pan and Xianglong Liu and Zeqi Ren and Dongquan Yi and Yinhao Liu and Ruobing Zuo and Ze Zhao and Huilin He and Nairong Zhang and Xinyi He and Xiao Tan and Jun Wang and Pan Fang and Wei Zeng and Jianan Su and Kaixin Shen and Jingtong Wu and Hao Li and Shuai Chen and Jiangming Yang and Tianyi Zhang},
  title = {{Antom 3-in-1 Transformer: A Payment Foundation Model}},
  year = {2026},
  eprint = {2611.25403},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.25403},
}
Figure