TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yeh, Chin-Chia Michael, Saini, Uday Singh, Dai, Xin, Fan, Xiran, Jain, Shubham, Fan, Yujie, Sun, Jiarui, Wang, Junpeng, Pan, Menghai, Dou, Yingtong, Chen, Yuzhong, Rakesh, Vineeth, Wang, Liang, Zheng, Yan, Das, Mahashweta
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917390784135168
author Yeh, Chin-Chia Michael
Saini, Uday Singh
Dai, Xin
Fan, Xiran
Jain, Shubham
Fan, Yujie
Sun, Jiarui
Wang, Junpeng
Pan, Menghai
Dou, Yingtong
Chen, Yuzhong
Rakesh, Vineeth
Wang, Liang
Zheng, Yan
Das, Mahashweta
author_facet Yeh, Chin-Chia Michael
Saini, Uday Singh
Dai, Xin
Fan, Xiran
Jain, Shubham
Fan, Yujie
Sun, Jiarui
Wang, Junpeng
Pan, Menghai
Dou, Yingtong
Chen, Yuzhong
Rakesh, Vineeth
Wang, Liang
Zheng, Yan
Das, Mahashweta
contents Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling this data can enable applications such as abnormal behavior detection and consumer-level insights for hyper-personalized experiences, ultimately improving people's lives. In this paper, we present TREASURE, TRansformer Engine As Scalable Universal transaction Representation Encoder, a multipurpose transformer-based foundation model specifically designed for transaction data. The model simultaneously captures both consumer behavior and payment network signals (such as response codes and system flags), providing comprehensive information necessary for applications like accurate recommendation systems and abnormal behavior detection. Verified with industry-grade datasets, TREASURE features three key capabilities: 1) an input module with dedicated sub-modules for static and dynamic attributes, enabling more efficient training and inference; 2) an efficient and effective training paradigm for predicting high-cardinality categorical attributes; and 3) demonstrated effectiveness as both a standalone model that increases abnormal behavior detection performance by 111% over production systems and an embedding provider that enhances recommendation models by 104%. We present key insights from extensive ablation studies, benchmarks against production models, and case studies, highlighting valuable knowledge gained from developing TREASURE.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19693
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
Yeh, Chin-Chia Michael
Saini, Uday Singh
Dai, Xin
Fan, Xiran
Jain, Shubham
Fan, Yujie
Sun, Jiarui
Wang, Junpeng
Pan, Menghai
Dou, Yingtong
Chen, Yuzhong
Rakesh, Vineeth
Wang, Liang
Zheng, Yan
Das, Mahashweta
Machine Learning
Artificial Intelligence
Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling this data can enable applications such as abnormal behavior detection and consumer-level insights for hyper-personalized experiences, ultimately improving people's lives. In this paper, we present TREASURE, TRansformer Engine As Scalable Universal transaction Representation Encoder, a multipurpose transformer-based foundation model specifically designed for transaction data. The model simultaneously captures both consumer behavior and payment network signals (such as response codes and system flags), providing comprehensive information necessary for applications like accurate recommendation systems and abnormal behavior detection. Verified with industry-grade datasets, TREASURE features three key capabilities: 1) an input module with dedicated sub-modules for static and dynamic attributes, enabling more efficient training and inference; 2) an efficient and effective training paradigm for predicting high-cardinality categorical attributes; and 3) demonstrated effectiveness as both a standalone model that increases abnormal behavior detection performance by 111% over production systems and an embedding provider that enhances recommendation models by 104%. We present key insights from extensive ablation studies, benchmarks against production models, and case studies, highlighting valuable knowledge gained from developing TREASURE.
title TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.19693