Researchers have developed the Large Payments Model (LPM), a novel foundation model specifically designed for operational use in payment applications. LPM is trained on extensive structured transaction data to create reusable representations for tasks like fraud detection and payment optimization. It features two architectures, Independent and Sequence, to handle heterogeneous transaction fields, high-cardinality identifiers, and long histories efficiently, while also supporting distillation for resource-constrained deployments. LPM has demonstrated improved performance over task-specific baselines in Merchant and Treasury Services and shows promise for adaptation to new payment domains. AI
IMPACT This model could streamline development and improve accuracy for various financial transaction applications.
RANK_REASON The cluster contains a research paper detailing a new foundation model for a specific domain. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- IArxiv Recommender
- Influence Flower
- Large Payments Model
- Merchant and Treasury Services
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
