公开(公告)号：US20240095742A1

公开(公告)日：2024-03-21

申请号：US17947956

申请日：2022-09-19

Applicant: Stripe, Inc.

Inventor： Caitlyn CHEN ,  Yucheng Tu ,  Amr Elroumy

IPC: G06Q20/40 ,  G06N20/00

CPC classification number: G06Q20/4016 ,  G06N20/00

Abstract: In an example embodiment, a solution is provided wherein a machine learning model is to determine a likelihood that a transaction is fraudulent, but also a separate machine learning model is used to determine a suitable threshold for a merchant. This predicted suitable threshold can either be automatically applied to the merchant, or can be recommended to the merchant (allowing the merchant to accept or reject it).

公开(公告)号：US20240070759A1

公开(公告)日：2024-02-29

申请号：US17897084

申请日：2022-08-26

Applicant: STRIPE, INC.

Inventor： Jimmy Jin ,  Hassaan Markhiani

IPC: G06Q30/06

CPC classification number: G06Q30/0639

Abstract: Examples of the present disclosure describe improved systems and methods for selection of candidate content items. In one example implementation a system includes a processor and a memory coupled to the processor. The memory includes a plurality of sets of requirements. Each set of requirements may be associated with a corresponding available content item of a plurality of available content items. A comparison module may be configured to compare a set of user parameters to each set of requirements and select two or more candidate content items from the plurality of available content items based on the set of user parameters satisfying the set of requirements. A bandit module may be configured to select one elected content item from the two or more candidate content items using a multi-armed bandit model. A user interface module may be configured to transmit the elected content item.

公开(公告)号：US20240070474A1

公开(公告)日：2024-02-29

申请号：US17894580

申请日：2022-08-24

Applicant: Stripe, Inc.

Inventor： Ariel SAGALOVSKY ,  Chiranth Manjunath Hegde

IPC: G06N5/00 ,  G06K9/62

CPC classification number: G06N5/003 ,  G06K9/6201 ,  G06K9/623 ,  G06K9/6262

Abstract: In an example embodiment, a random forest machine learning algorithm is used to create and/or identify rules to apply to an individual entity in a computer system that has a plurality of entities, each with a number of rules. More precisely, rule predicates are used as features of a random forest model built to predict a particular outcome (e.g., a transaction that is fraudulent). Hyperparameters of the random forest model are varied and iterated. A classifier is used to calculate feature importance for all features in the training data. Feature importance may be calculated using permutation feature importance. The N “most important” features are then found from this set. The N “most important” features are then used to find rules above a certain precision and recall rate. These rules may then be backtested and the best rules can be used to generate additional rules.

公开(公告)号：US20240061927A1

公开(公告)日：2024-02-22

申请号：US18501756

申请日：2023-11-03

Applicant: STRIPE, INC.

Inventor： Karla Burnett ,  Andrew Reitz ,  Yasha Mostofi-Ashtiani ,  Jason Shantz ,  Justin Sippel ,  Andrew Dunham ,  Shawn Moore ,  Adam Zev Sorkin

IPC: G06F21/53 ,  G06F8/30 ,  G06F21/56

CPC classification number: G06F21/53 ,  G06F8/30 ,  G06F21/56 ,  G06F2221/2141

Abstract: A method and apparatus for executing code in a container are described. In one embodiment, the method comprises generating code on a host computer system using a user interface; and executing the code inside a container on the host computer system, including performing access control based on one or more properties of the host computer system.

公开(公告)号：US11899663B2

公开(公告)日：2024-02-13

申请号：US17476243

申请日：2021-09-15

Applicant: Stripe, Inc.

Inventor： Alisa (Shuhui) He ,  Tushar Dhoot ,  Ji Huang

IPC: G06F16/245 ,  G06F16/24 ,  G06F16/2453 ,  G06F16/242

CPC classification number: G06F16/24539 ,  G06F16/244

Abstract: In an example embodiment, a solution is provided that aggregates records as they are submitted to a third party (on the write path) rather than performing a real-time aggregation when a request is processed that needs the aggregation (read path). More particularly, in an example embodiment, a caching layer is introduced that avoids having to read all usage events to compute an aggregation when a request is received for aggregated data. The caching layer maintains values for various metrics that require aggregation.

公开(公告)号：US20240037011A1

公开(公告)日：2024-02-01

申请号：US17873833

申请日：2022-07-26

Applicant: Stripe, Inc.

Inventor： Sydney ZHENG ,  Soam Vasani

IPC: G06F11/36 ,  G06N20/00

CPC classification number: G06F11/3608 ,  G06F11/3664 ,  G06N20/00

Abstract: In an example embodiment, interactions among services in a service proxy are recorded in an interaction log. A service graph manager then parses the interaction log. The service graph manager reads each interaction and then processes the interaction to determine if it violates the rules. If so, the service graph manager reports the violation to the software developer and also recommends an action to remedy the violation. In an example embodiment, this recommendation takes the form of an indication of which files to modify to allow the service interaction (e.g., which rule(s) to modify to ensure that the service interaction is not a violation). The software developer can then approve the proposed action, which can then be automatically implemented to ensure that once the service is sent to a quality assurance environment there will be no rules violation from the corresponding interaction(s).

公开(公告)号：US20240020702A1

公开(公告)日：2024-01-18

申请号：US18373845

申请日：2023-09-27

Applicant: Stripe, Inc.

Inventor： Jonathan Wall

IPC: G06Q20/40 ,  G06Q20/42 ,  G06Q20/34 ,  G06Q20/38

CPC classification number: G06Q20/4018 ,  G06Q20/425 ,  G06Q20/341 ,  G06Q20/3827 ,  G06Q20/3829 ,  G06Q20/409

Abstract: A method and apparatus for processing a transaction between a merchant and a customer of the merchant are described. The method may include generating, at an ingress server, an initial transaction message by generating a deterministic identifier for a card used in the transaction from card data received for the transaction and encrypting the received card data. The method may also include providing the initial transaction message from the ingress server to a payment server. Furthermore, the method may include updating, by the payment server in response to an authorization of the transaction determined based at least in part on the deterministic identifier for the card, the initial transaction message with authorization data, and providing the updated initial transaction message from the payment server to an egress server. The method may also include communicating a final transaction message to an authorization system for processing the transaction between the merchant and the customer based on the card data.

公开(公告)号：US20230421563A1

公开(公告)日：2023-12-28

申请号：US17846489

申请日：2022-06-22

Applicant: Stripe, Inc.

Inventor： Aaltan Ahmad ,  Surbhi Shah ,  Matthew Moresco

IPC: H04L9/40

CPC classification number: H04L63/102 ,  H04L63/20

Abstract: Various embodiments include systems, methods, and non-transitory computer-readable media for managing access control. Consistent with these embodiments, a method includes receiving a request to access a resource, determining one or more access control policies that correspond to an access to the resource; identifying an access control policy that allows the identity to access the resource, determining, that the identified access control policy is associated with a policy evaluation mode, and authorizing the request based on the access control policy.

公开(公告)号：US11811604B2

公开(公告)日：2023-11-07

申请号：US17204398

申请日：2021-03-17

Applicant: STRIPE, INC.

Inventor： Tanin Na Nakorn ,  Ji Huang

IPC: H04L41/0869 ,  G06F11/36

CPC classification number: H04L41/0869 ,  G06F11/3664 ,  G06F11/3688

Abstract: A method and apparatus for performing cross-platform contract validation are described. In one embodiment, the method for validating compatibility between first and second endpoints, the method comprising: accessing a memory storing a machine-readable contract specifying a request-response pair in a file, the request-response pair consisting of an expected request that the second endpoint expects to receive from the first endpoint and an expected response that should be provided by the second endpoint according to the expected request from the first endpoint; and performing multi-platform contract validation by performing independent tests for the first and second endpoints, using the expected request and expected response specified in the machine-readable contract.

公开(公告)号：US11809863B2

公开(公告)日：2023-11-07

申请号：US17521639

申请日：2021-11-08

Applicant: Stripe, Inc.

Inventor： William Story ,  David Hwang

IPC: G06F8/71 ,  G06N20/00 ,  G06F9/455 ,  H04L9/06

CPC classification number: G06F8/71 ,  G06F9/45558 ,  G06N20/00 ,  H04L9/0643 ,  G06F2009/45562 ,  G06F2009/45595

Abstract: The subject technology detects a code commit at a code repository. The subject technology sends a request for a build job to a build server. The subject technology determines that the build job is completed. The subject technology sends a training request and user token to a proxy authenticator. The subject technology determines determining that the user token is validated. The subject technology sends a training request and the user token to a training job manager. Further, the subject technology determines determining that the training job is completed.