TransactionGPT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dou, Yingtong, Jiang, Zhimeng, Zhang, Tianyi, Hu, Mingzhi, Xu, Zhichao, Jain, Shubham, Saini, Uday Singh, Fan, Xiran, Sun, Jiarui, Pan, Menghai, Wang, Junpeng, Dai, Xin, Wang, Liang, Yeh, Chin-Chia Michael, Fan, Yujie, Zheng, Yan, Rakesh, Vineeth, Chen, Huiyuan, Wang, Guanchu, Bendre, Mangesh, Zhuang, Zhongfang, Li, Xiaoting, Aboagye, Prince, Lai, Vivian, Xu, Minghua, Yang, Hao, Cai, Yiwei, Das, Mahashweta, Chen, Yuzhong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917307493646336
author Dou, Yingtong
Jiang, Zhimeng
Zhang, Tianyi
Hu, Mingzhi
Xu, Zhichao
Jain, Shubham
Saini, Uday Singh
Fan, Xiran
Sun, Jiarui
Pan, Menghai
Wang, Junpeng
Dai, Xin
Wang, Liang
Yeh, Chin-Chia Michael
Fan, Yujie
Zheng, Yan
Rakesh, Vineeth
Chen, Huiyuan
Wang, Guanchu
Bendre, Mangesh
Zhuang, Zhongfang
Li, Xiaoting
Aboagye, Prince
Lai, Vivian
Xu, Minghua
Yang, Hao
Cai, Yiwei
Das, Mahashweta
Chen, Yuzhong
author_facet Dou, Yingtong
Jiang, Zhimeng
Zhang, Tianyi
Hu, Mingzhi
Xu, Zhichao
Jain, Shubham
Saini, Uday Singh
Fan, Xiran
Sun, Jiarui
Pan, Menghai
Wang, Junpeng
Dai, Xin
Wang, Liang
Yeh, Chin-Chia Michael
Fan, Yujie
Zheng, Yan
Rakesh, Vineeth
Chen, Huiyuan
Wang, Guanchu
Bendre, Mangesh
Zhuang, Zhongfang
Li, Xiaoting
Aboagye, Prince
Lai, Vivian
Xu, Minghua
Yang, Hao
Cai, Yiwei
Das, Mahashweta
Chen, Yuzhong
contents We present TransactionGPT (TGPT), a foundation model for consumer transaction data within one of the world's largest payment networks. TGPT is designed to understand and generate transaction trajectories while simultaneously supporting a variety of downstream prediction and classification tasks. We introduce a novel 3D-Transformer architecture specifically tailored for capturing the complex dynamics in payment transaction data. This architecture incorporates design innovations that enhance modality fusion and computational efficiency, while seamlessly enabling joint optimization with downstream objectives. Trained on billion-scale real-world transactions, TGPT significantly improves downstream anomaly transaction detection performance against a competitive production model and exhibits advantages over baselines in generating future transactions. We conduct extensive empirical evaluations utilizing a diverse collection of company transaction datasets spanning multiple downstream tasks, thereby enabling a thorough assessment of TGPT's effectiveness and efficiency in comparison to established methodologies. Furthermore, we examine the incorporation of LLM-derived embeddings within TGPT and benchmark its performance against fine-tuned LLMs, demonstrating that TGPT achieves superior predictive accuracy as well as faster training and inference. We anticipate that the architectural innovations and practical guidelines from this work will advance foundation models for transaction-like data and catalyze future research in this emerging field.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TransactionGPT
Dou, Yingtong
Jiang, Zhimeng
Zhang, Tianyi
Hu, Mingzhi
Xu, Zhichao
Jain, Shubham
Saini, Uday Singh
Fan, Xiran
Sun, Jiarui
Pan, Menghai
Wang, Junpeng
Dai, Xin
Wang, Liang
Yeh, Chin-Chia Michael
Fan, Yujie
Zheng, Yan
Rakesh, Vineeth
Chen, Huiyuan
Wang, Guanchu
Bendre, Mangesh
Zhuang, Zhongfang
Li, Xiaoting
Aboagye, Prince
Lai, Vivian
Xu, Minghua
Yang, Hao
Cai, Yiwei
Das, Mahashweta
Chen, Yuzhong
Machine Learning
Computation and Language
We present TransactionGPT (TGPT), a foundation model for consumer transaction data within one of the world's largest payment networks. TGPT is designed to understand and generate transaction trajectories while simultaneously supporting a variety of downstream prediction and classification tasks. We introduce a novel 3D-Transformer architecture specifically tailored for capturing the complex dynamics in payment transaction data. This architecture incorporates design innovations that enhance modality fusion and computational efficiency, while seamlessly enabling joint optimization with downstream objectives. Trained on billion-scale real-world transactions, TGPT significantly improves downstream anomaly transaction detection performance against a competitive production model and exhibits advantages over baselines in generating future transactions. We conduct extensive empirical evaluations utilizing a diverse collection of company transaction datasets spanning multiple downstream tasks, thereby enabling a thorough assessment of TGPT's effectiveness and efficiency in comparison to established methodologies. Furthermore, we examine the incorporation of LLM-derived embeddings within TGPT and benchmark its performance against fine-tuned LLMs, demonstrating that TGPT achieves superior predictive accuracy as well as faster training and inference. We anticipate that the architectural innovations and practical guidelines from this work will advance foundation models for transaction-like data and catalyze future research in this emerging field.
title TransactionGPT
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2511.08939