cs.LGNov 11, 2026

Large Payments Model

Authors: Natraj Raman, Abhenandhan Manoharan, Vishwasreddy Thuniki, Dhvani Kansara, Anirudh Som, Hassan Firouzi, Kostis Gourgoulias, Laukik Hoshing, 

Organizations: JPMorgan Chase & Co

Abstract

Payment applications such as fraud detection, authorization prediction, and payment optimization draw on overlapping transaction information. This motivates a reusable payments intelligence layer that shares learned representations and predictive signals, rather than developing predictive models independently for each task. Realizing this shared capability requires handling heterogeneous transaction fields, high-cardinality identifiers, lifecycle-dependent attributes, long histories, and rare outcomes while meeting latency and cost constraints. We present Large Payments Model (LPM), a domain-specific foundation model designed for operational use and trained from scratch on large-scale structured transaction data to learn reusable representations for payment prediction tasks. LPM employs field-specific encodings and lifecycle-aware self-supervision in two complementary architectures: the Independent variant uses hybrid masking and supports efficient per-transaction inference, while the Sequence variant incorporates entity-linked histories through compact latent representations for richer temporal context. Optional distillation enables resource-constrained deployment. We pretrain LPM on up to 400 billion tokens and study scaling, downstream performance, and representation reuse. LPM improves over strong task-specific baselines across multiple prediction tasks in Merchant and Treasury Services, demonstrating applicability in distinct payment domains. Its representations also facilitate adaptation to a target not observed during pretraining through compact task-specific components. Together with production deployment, these results position LPM as a practical basis for reusable payments intelligence.

Figures & tables

Explore similar work

CardsList
  1. Multimodal Zero-Shot Prediction for Transaction Data at Scale

    Aug 14, 2026Parameswaran Kamalaruban, Viktor Drobnyi, Maeve Madigan +3Zero-Shot LearningMultimodal Foundation Models

  2. TRIDENT-Seq: Profile-Matched Prefix-Future Contrast for Label-Efficient Payment Risk Modeling

    Oct 27, 2026Weiyu Han, Haoyu Jiang, Jie Sheng +7Financial Fraud DetectionContrastive Learning

  3. PRAGMA: Revolut Foundation Model

    Apr 9, 2026Maxim Ostroukhov, Ruslan Mikhailov, Vladimir Iashin +11Masked ModelingFinancial Services