Stripe had 22 patents in artificial intelligence during Q2 2024. Stripe Inc has developed methods and apparatus for detecting fraudulent merchant activities on commerce platform systems by utilizing machine learning models to generate fraud scores and taking actions based on those scores. Additionally, systems and methods have been created for identifying and transmitting electronic requests to suitable service providers based on verification success likelihood and service provider attributes. Furthermore, a system has been designed to store and reference payment card scan data to determine the legitimacy of transactions without requiring the customer to rescan their card. GlobalData’s report on Stripe gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Stripe had no grants in artificial intelligence as a theme in Q2 2024.
Recent Patents
Application: Systems and methods for merchant level fraud detection based in part on merchant cohort clustering (Patent ID: US20240211965A1)
The patent filed by Stripe Inc. describes a method and apparatus for detecting fraudulent merchant activities at a commerce platform system. The method involves accessing signal data for merchant system transactions, encoding the data into input signals, inputting these signals into machine learning models to generate fraud scores, clustering merchant systems based on input signals, and generating cluster fraud scores. If a cluster fraud score surpasses a threshold, remedial actions are taken against each merchant system in the cluster, such as suspending or deactivating accounts. The system uses a combination of machine learning models like XGBoost and Neural Network, and clustering techniques like density-based spatial clustering or KMeans clustering.
The patent also details the structure of the signal data, which includes both structured and unstructured data, as well as merchant system characteristics like transaction volume, location, and fraud detection history. The method calculates cluster fraud scores based on probabilities of fraud, average fraud scores, and maximum fraud scores within each cluster. Additionally, the system can group merchant systems into different cohort clusters based on machine learning model outputs and performs clustering periodically. The patent also covers a computer-readable storage medium storing instructions for the method and a server computer system configured to detect fraudulent merchant activities using the described operations.
To know more about GlobalData’s detailed insights on Stripe, 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.
