arXiv cs.AI· Natraj Raman, Abhenandhan Manoharan, Vishwasreddy Thuniki, Dhvani Kansara, Anirudh Som, Hassan Firouzi, Kostis Gourgoulias, Laukik Hoshing, Sudhir Kanala, Austin Reiter, Ebby Abdul, Shantanu Chandra, Ryan Schmiedl, Zack Anderson, Sumitra Ganesh·· 3 小时前AI 评分50
JPMorgan 团队发布支付领域基础模型 Large Payments Model（LPM）
Large Payments Model
AI 导读
arXiv 论文 arXiv:2611.15814 提出 Large Payments Model（LPM），一个在大规模结构化交易数据上从零预训练的支付领域基础模型，服务于欺诈检测、授权预测和支付优化等任务。
正文 · 原文
Authors:Natraj Raman, Abhenandhan Manoharan, Vishwasreddy Thuniki, Dhvani Kansara, Anirudh Som, Hassan Firouzi, Kostis Gourgoulias, Laukik Hoshing, Sudhir Kanala, Austin Reiter, Ebby Abdul, Shantanu Chandra, Ryan Schmiedl, Zack Anderson, Sumitra Ganesh
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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2611.15814 [cs.LG] |
| (or arXiv:2611.15814v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15814 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Natraj Raman [view email]
[v1]
Wed, 11 Nov 2026 18:30:35 UTC (1,066 KB)
来源：arXiv cs.AI · arxiv.org