Processing Machine Learning Attributes

Patent metadata

Field	Value
Publication number	US-2022180231-A1
Application number	US-202217681480-A
Country	US
Kind code	A1
Filing date	Feb 25, 2022
Priority date	Oct 18, 2016
Publication date	Jun 9, 2022
Grant date	—

Abstract

Systems and methods for processing machine learning attributes are disclosed. An example method includes: identifying a user transaction associated with a set of transaction attributes and a first transaction status; selecting, based on a risk evaluation model, a first plurality of transaction attributes from the set of transaction attributes; modifying a first value of a first transaction attribute in the first plurality of transaction attributes to produce a first modified plurality of transaction attributes; determining, based on the risk evaluation model, that the first modified plurality of transaction attributes identify a second transaction status different from the first transaction status; and in response to the determining, identifying the first transaction attribute as a risk attribute associated with the user transaction.

First claim

What is claimed is:

1 . A computer system, comprising:
a processor; and a non-transitory computer-readable medium having stored thereon instructions that are executable to cause the computer system to perform operations comprising: receiving information indicating a request to perform an electronic transaction between a user of a user device and a merchant associated with a merchant device, wherein the request comprises a plurality of attribute values corresponding to a plurality of transaction attributes associated with the electronic transaction; determining, using a risk evaluation model, that the request is associated with a first risk above a predefined amount, wherein the risk evaluation model indicates that the request should be denied based on the first risk being above the predefined amount; determining, using the risk evaluation model, at least a specific machine learning attribute from a set of machine learning attributes, wherein a specific value for the specific machine learning attribute contributes to the first risk being above the predefined amount based on a plurality of modified transaction requests, wherein the plurality of modified transaction requests are generated by modifying different ones of the plurality of transaction attributes associated with the electronic transaction; generating an indication that the request is denied based on the specific machine learning attribute; and transmitting, to the user of the user device, response information including the indication that the request is denied based on the specific machine learning attribute.

2 . The computer system of claim 1 , wherein the operations further comprise:
receiving, via the user of the user device, additional information regarding the specific machine learning attribute; and processing the electronic transaction based on the additional information.

3 . The computer system of claim 1 , wherein the operations further comprise:
transmitting the indication that the request is denied to the user device.

4 . The computer system of claim 1 , wherein the operations further comprise:
generating the plurality of modified transaction requests based on a first selected subset of the set of machine learning attributes.

5 . The computer system of claim 1 , wherein the information indicating the request to perform the electronic transaction is received via the merchant device.

6 . The computer system of claim 1 , wherein the plurality of transaction attributes comprise a user transaction frequency level.

7 . A method, comprising:
receiving, at a computer system, information indicating a request to perform an electronic transaction between a user of a user device and a merchant associated with a merchant device, wherein the request comprises a plurality of attribute values corresponding to a plurality of transaction attributes associated with the electronic transaction; determining, by the computer system using a risk evaluation model, that the request is associated with a first risk above a predefined amount, wherein the risk evaluation model indicates that the request should be denied based on the first risk being above the predefined amount; determining, by the computer system using the risk evaluation model, at least a specific machine learning attribute from a set of machine learning attributes, wherein a specific value for the specific machine learning attribute contributes to the first risk being above the predefined amount based on a plurality of modified transaction requests, wherein the plurality of modified transaction requests are generated by modifying different ones of the plurality of transaction attributes associated with the electronic transaction; generating an indication that the request is denied based on the specific machine learning attribute; and transmitting, to the user of the user device, response information including the indication that the request is denied based on the specific machine learning attribute.

8 . The method of claim 7 , wherein the plurality of transaction attributes includes an IP address, and wherein the specific value for the specific machine learning attribute comprises an IP address for the user device.

9 . The method of claim 7 , wherein the plurality of transaction attributes includes a purchase amount, and wherein the specific value for the specific machine learning attribute comprises a specific purchase amount corresponding to the request.

10 . The method of claim 7 , wherein the plurality of transaction attributes includes a description of an item being purchased, and wherein the specific value for the specific machine learning attribute comprises a specific item description corresponding to the request.

11 . The method of claim 7 , further comprising:
receiving, via the user of the user device, additional information regarding the specific machine learning attribute; and processing the electronic transaction based on the additional information.

12 . The method of claim 7 , further comprising:
transmitting the indication that the request is denied to the user device.

13 . The method of claim 7 , further comprising:
generating the plurality of modified transaction requests based on a first selected subset of the set of machine learning attributes.

14 . The method of claim 7 , further comprising, wherein the information indicating the request to perform the electronic transaction is received via the merchant device.

15 . A non-transitory computer-readable medium having stored thereon instructions that are executable to cause a computer system to perform operations comprising:
receiving information indicating a request to perform an electronic transaction between a user of a user device and a merchant associated with a merchant device, wherein the request comprises a plurality of attribute values corresponding to a plurality of transaction attributes associated with the electronic transaction; determining, using a risk evaluation model, that the request is associated with a first risk above a predefined amount, wherein the risk evaluation model indicates that the request should be denied based on the first risk being above the predefined amount; determining, using the risk evaluation model, at least a specific machine learning attribute from a set of machine learning attributes, wherein a specific value for the specific machine learning attribute contributes to the first risk being above the predefined amount based on a plurality of modified transaction requests, wherein the plurality of modified transaction requests are generated by modifying different ones of the plurality of transaction attributes associated with the electronic transaction; generating an indication that the request is denied based on the specific machine learning attribute; and transmitting, to the user of the user device, response information including the indication that the request is denied based on the specific machine learning attribute.

16 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:
receiving, via the user of the user device, additional information regarding the specific machine learning attribute; and processing the electronic transaction based on the additional information.

17 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:
transmitting the indication that the request is denied to the user device.

18 . The non-transitory computer-readable medium of claim 15 , wherein the oper

Assignees

• Paypal Inc

Inventors

• Lin Ying
• Yin Huagang
• Zhang Jiaqi

Classifications

• G06N5/045 Primary

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G06Q20/4016

  involving fraud or risk level assessment in transaction processing · CPC title