This inventor holds 1 USPTO granted patent and 2 published patent applications. Top assignee: Visa International Service Association. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Innovations by Can Liu in Transaction Data Sampling
Introduction
Can Liu is an accomplished inventor based in Lucas, TX (US). He has made significant contributions to the field of transaction data analysis, particularly in addressing the challenges posed by imbalanced transactions. His innovative approach has led to the development of a unique sampling framework that enhances the efficiency of transaction data processing.
Latest Patents
Can Liu holds a patent for a "Sampling framework for imbalanced transactions." This invention involves a server computer that implements an efficient sampling technique for imbalanced transactions. The process encodes transaction data, which includes both unlabeled and fraudulent transaction data, into two distinct sets. The first set is associated with fraudulent transactions and similar unlabeled transactions, while the second set pertains to unlabeled transactions. The invention executes a first sampling process on the first set to obtain a sampled set and a second sampling process on the second set to achieve another sampled set. The optimal sampling size is determined based on the performance of a machine learning model that classifies these sampled sets.
Career Highlights
Can Liu is currently employed at Visa International Service Association, where he applies his expertise in transaction data analysis. His work focuses on improving the accuracy and efficiency of fraud detection systems through innovative sampling techniques.
Collaborations
Can Liu collaborates with talented professionals in his field, including Yong Zhao and Shubham Agrawal. Their combined efforts contribute to advancing the technology and methodologies used in transaction data processing.
Conclusion
Can Liu's innovative contributions to the field of transaction data sampling demonstrate his commitment to enhancing fraud detection systems. His patent reflects a significant advancement in the efficient handling of imbalanced transactions, showcasing his expertise and dedication to innovation.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile