Stripe had 45 patents in digitalization during Q2 2024. Stripe Inc filed patents related to detecting fraudulent merchant activities at a commerce platform system using machine learning models to generate fraud scores and taking remedial actions when fraud is detected. Another patent involves a server computer system processing transactions and authorizing payments. Additionally, there is a patent for rendering components of a webpage with embedded UI elements from a third-party entity using a secret token for authentication. The patents focus on detecting fraud through analyzing different types of data and taking appropriate actions to prevent fraudulent activities. 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 digitalization as a theme in Q2 2024.
Recent Patents
Application: Systems and methods for merchant level fraud detection using an ensemble of machine learning models (Patent ID: US20240211966A1)
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 different types of merchant system data, encoding the data into structured and unstructured sets, inputting them into machine learning models to generate fraud predictions, combining the fraud scores to generate a single merchant fraud score, and initiating remedial actions if the fraud score meets a threshold. The system uses machine learning models like XGBoost and Neural Network to analyze structured and unstructured data, such as transaction amounts and text data like email addresses, to detect fraud.
The method further includes actions like declining transactions, deactivating accounts, or sending fraud detection messages based on the fraud score. The system also involves annotating transaction data with feedback from the merchant system, storing annotated data for training, and periodically retraining the machine learning models. The single merchant fraud score is generated in real-time or near real-time, allowing for quick analysis before processing transactions. Overall, the patent outlines a comprehensive approach to detecting and preventing fraudulent merchant activities using a combination of structured and unstructured data analysis and machine learning models.
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.
