Visa. has been granted a patent for a computer-implemented method utilizing a generative adversarial network (GAN) to classify accounts based on merchant activation. The method involves generating datasets and training both generator and discriminator networks to predict payment transaction behaviors. GlobalData’s report on Visa gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Visa, Contactless Card Payments was a key innovation area identified from patents. Visa's grant share as of July 2024 was 44%. Grant share is based on the ratio of number of grants to total number of patents.
Machine learning model for classifying payment transaction accounts
The patent US12073330B2 describes a computer-implemented method utilizing a generative adversarial network (GAN) to generate and evaluate datasets related to payment transactions. The method involves providing an input to a generator network, which includes a first dataset and randomly generated data fed into machine learning models, specifically XGBoost and Neural Collaborative Filtering. The output from these models serves as input to the generator network, which produces a generated dataset containing various features associated with payment transactions, such as time intervals, market segments, transaction amounts, and total amounts over specified time intervals. This generated dataset is then used as input for a discriminator network, which is trained to determine the likelihood of a selected account conducting a transaction with a merchant.
The patent further details the architecture of both the generator and discriminator networks, specifying the configuration of dense layers and activation functions, including ReLU and sigmoid functions. It also outlines training procedures that incorporate dropout and batch normalization processes to enhance model performance. Additionally, the method includes optimizing the discriminator network based on a recall formula, which measures the accuracy of predictions against ground truth labels. This innovative approach aims to improve the generation and evaluation of transaction-related data, potentially benefiting various applications in financial technology and data analysis.
To know more about GlobalData’s detailed insights on Visa, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
