Stripe, Inc. patent applications on May 30th, 2024
Patent Applications by Stripe, Inc. on May 30th, 2024
Stripe, Inc.: 5 patent applications
Stripe, Inc. has applied for patents in the areas of G06Q20/40 (4), G06V30/41 (4), G06Q20/4016 (3), G06V10/774 (2), G06V10/82 (2)
With keywords such as: image, document, data, include, learning, transaction, service, machine, request, and identity in patent application abstracts.
Patent Applications by Stripe, Inc.
Inventor(s): Yiran SHENG of London (GB) for stripe, inc., Omer Zach of New York NY (US) for stripe, inc., Alexander Joseph McLeod of San Francisco CA (US) for stripe, inc.
IPC Code(s): G06Q20/40, G06Q20/10
CPC Code(s):
Abstract: in an example embodiment, a system is provided that allows for multiple service partners to be accessible simultaneously via a single api. the system ensures that requests to collect payment information are sent only to a service partner that is active and operating, ensuring that a request to collect payment information that would normally have been sent to a service partner that is down or otherwise unavailable will be rerouted to an alternative service partner. furthermore, the system also allows for a dynamic selection of a service partner to utilize among multiple service providers, based on factors such as how well the service provider's system integrates with the underlying institution from which the payment will be made, and the estimated speed of the processing of the transaction by the service provider. this latter aspect can be technically challenging because the same institution may be known by multiple different names on the different service providers.
Inventor(s): Charlotte Gils of Mont-Saint-Hilaire (CA) for stripe, inc., Efstathios Vafeias of London (GB) for stripe, inc.
IPC Code(s): G06Q20/40, G06V10/774, G06V10/82, G06V20/00, G06V30/41
CPC Code(s):
Abstract: a method and apparatus for fraud detection during transactions using identity graphs are described. the method may include receiving a document image for detecting whether an identity document depicted within the document image is fraudulent. the method may also include extracting data associated with the document image to generate extracted data. the method may also include processing, by a single machine learning model, subsets of the decoded image data used as corresponding inputs to each of a set of machine learning model backbones of the single machine learning model that generate one or more intermediate signals indicative of whether a subset of the extracted image data input into said each machine learning model backbone is associated with a fraudulent identity document. the method may also include processing, by a second machine learning model backbone that generates a final score indicative of whether the document image depicts a fraudulent identity document, at least one or more intermediate signals.
Inventor(s): Isaac MADWED of Seattle WA (US) for stripe, inc., Ryan DRAPEAU of Seattle WA (US) for stripe, inc.
IPC Code(s): G06Q20/40
CPC Code(s):
Abstract: a method and apparatus for generating an ml model may include: generating an ml feature template comprising a first grouping of first ml feature variables and a second grouping of second ml feature variables; generating ml features by combining a respective one of each of the first ml feature variables with a respective one of each of the second ml feature variables; training a first ml model utilizing the ml features and first training data to generate an ml output; analyzing the ml output to determine a prediction accuracy of the ml features; based on the prediction accuracy of the ml features, selecting a subset of the ml features; training a second ml model based on the subset of the ml features and the first training data; and providing a network transaction to the second ml model to generate a classification of the network transaction.
Inventor(s): Fanyun FANG of San Francisco CA (US) for stripe, inc., Aakash SAHNEY of Sherman Oaks CA (US) for stripe, inc., Christopher Jeffery STREETER of Ardmore PA (US) for stripe, inc., Kevin Chekin HO of New York NY (US) for stripe, inc., David LAKATA of Brooklyn NY (US) for stripe, inc.
IPC Code(s): G06Q20/40, G06Q30/06
CPC Code(s):
Abstract: a method and apparatus for processing a transaction request associated with a merchant platform system may include: receiving, at a commerce platform system, the transaction request; determining a plurality of account traits associated with the merchant platform system; detecting a first account trait from the plurality of account traits associated with the merchant platform system; in response to determining that the first account trait of the plurality of account traits comprises a first value, processing the transaction request to generate an approval status for the transaction request based on a risk value determined by the commerce platform system with respect to the transaction request; and in response to determining that the first account trait of the plurality of account traits comprises a second value, deferring a determination of the risk value for the transaction request to the merchant platform system.
Inventor(s): Charlotte Gils of Mont-Saint-Hilaire (CA) for stripe, inc., Efstathios Vafeias of London (GB) for stripe, inc.
IPC Code(s): G06V30/19, G06F40/169, G06V30/41
CPC Code(s):
Abstract: a method and apparatus for fraud detection during transactions using identity graphs are described. the method may include receiving a document image for detecting whether an identity document depicted within the document image is fraudulent. the method may also include extracting data associated with the document image to generate extracted data comprising image data extracted from the document image, image file data extracted from an image file for the document image, or a combination thereof. the method may also include processing, by a set of machine learning models, corresponding subsets of the decoded image data used as input to each machine learning model of the set of machine learning models, and further by a second machine learning model that generates a final score indicative of whether the document image depicts a fraudulent identity document, at least one or more initial scores.
