Abstract
When investigating an abnormal user account behavior, identification of behavior information of historical counterparties associated with the user account may be very significant. The present disclosure addresses this requirement by providing an AI-based framework that extracts and incorporates historical counterparty behavior for accurate prediction and estimation of current user behavior. The present disclosure provides an end-to-end framework that captures historical counterparty behaviors in financial transactions. The present disclosure provides an efficient data sampling technique for framework training. The present disclosure provides a training strategy for efficiently training the framework.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Liu, Can; Zhao, Yong; Xu, Hao; Agrawal, Shubham; and Chetia, Chiranjeet, "COUNTERPARTY AWARENESS USER BEHAVIOR EXTRACTION FRAMEWORK", Technical Disclosure Commons, (March 06, 2024)
https://www.tdcommons.org/dpubs_series/6753