Systems and methods for authenticating an electronic transaction

Patent metadata

Field	Value
Publication number	US-11397950-B2
Application number	US-201916601091-A
Country	US
Kind code	B2
Filing date	Oct 14, 2019
Priority date	Jun 20, 2019
Publication date	Jul 26, 2022
Grant date	Jul 26, 2022

Abstract

Devices and methods for securing electronic transactions in a computing network are configured to receive a transaction, access transaction contextual data for the transaction, and apply one or more authentication decision rules to the transaction contextual data to determine initial authentication assessment information for the transaction. Further, aspects are configured to convert the initial authentication assessment information into a condensed authentication assessment indicator having an assessment value selected from a plurality of assessment values based on an assessment value definition, and transmit the condensed authentication assessment indicator. Also, aspects receive a transaction authentication decision based in part on the condensed authentication assessment indicator, and process or deny processing of the transaction based on the transaction authentication decision.

First claim

What is claimed is:

1. A computer device for securing electronic transactions in a computing network, comprising:
a memory to store data and instructions;
at least one processor configured to communicate with the memory; and
an operating system in communication with the memory and the at least one processor, wherein the operating system is operable to:
receive a transaction;
access transaction contextual data for the transaction;
apply one or more authentication decision rules to the transaction contextual data to determine initial authentication assessment information for the transaction;
convert the initial authentication assessment information into a condensed authentication assessment indicator having an assessment value selected from a plurality of assessment values based on an assessment value definition;
transmit, by the computer device to a payment processor, the condensed authentication assessment indicator for the transaction;
receive, by the computer device from the payment processor, a transaction authentication decision based in part on the condensed authentication assessment indicator, wherein the condensed authentication assessment indicator comprises a standard format configured to provide the initial authentication assessment information as quantitative and consistent information or definitions that are interpreted in a same way by the computer device and by the payment processor;
process or deny processing the transaction, by the computer device, based on the transaction authentication decision; and
periodically train the one or more authentication decision rules via a machine learning model using historical transaction data, wherein latency in receiving completed or true authenticity labels from the payment processor for some historical transactions causes the machine learning model to be trained using partially obtained authenticity labels to forecast complete authenticity volume for each score bin.

2. The computer device of claim 1 , wherein the assessment value corresponds to an authentication category variable of a plurality of authentication category variables associated with the transaction, wherein the authentication category variable and the assessment value identify an initial assessed level of authenticity of the transaction.

3. The computer device of claim 1 , wherein the assessment value of the condensed authentication assessment indicator comprises a binary value.

4. The computer device of claim 1 , wherein the assessment value of the condensed authentication assessment indicator comprises an ordinal value.

5. The computer device of claim 1 , wherein the condensed authentication assessment indicator comprises a plurality of different assessment category values associated with a plurality of different authentication category variables, wherein each of the plurality of different authentication category variables correspond to a different one of a plurality of authenticity assessment factors, and wherein each of the plurality of different assessment category values is based on a different one of a plurality of different assessment category value definitions.

6. The computer device of claim 5 , wherein the plurality of authenticity assessment factors are selected from a group consisting of a transaction assessment factor, a device history assessment factor, a location assessment factor, a transaction data assessment factor, and a combined factor assessment factor.

7. The computer device of claim 1 , wherein the standard format of the condensed authentication assessment indicator is determined in response to one or more of an amount of data supported by a channel being used to transmit the condensed authentication assessment indicator or a time limit for authorizing the transaction.

8. The computer device of claim 1 , wherein the standard format of the condensed authentication assessment indicator includes one or more of a binary signal, a single indicator variable, a description, two or more indicator variables, or a raw data variable.

9. The computer device of claim 1 , wherein the condensed authentication assessment indicator provides the quantitative and consistent information or definitions for use with determining the transaction authentication decision.

10. The computer device of claim 1 , wherein the operating system is further operable to:
perform a calibration process on the initial authentication assessment information to minimize errors in the initial authentication assessment information, wherein the calibration process converts the initial authentication assessment information into normalized variables and normalized variable values that are interpreted in the same way by the computer device and by the payment processor.

11. The computer device of claim 1 , wherein the payment processor is associated with a payment instrument identified in the transaction contextual data, wherein, in order to transmit the condensed authentication assessment indicator and receive the transaction authentication decision, the operating system is further operable to:
transmit, from the computer device to the payment processor via a transaction network, the condensed authentication assessment indicator by using a secondary data channel; and
receive, by the computer device from the payment processor via the transaction network, the transaction authentication decision based in part on the condensed authentication assessment indicator.

12. A method of securing electronic transactions in a computing network, comprising:
receiving a transaction;
accessing transaction contextual data for the transaction;
applying one or more authentication decision rules to the transaction contextual data to determine initial authentication assessment information for the transaction;
converting the initial authentication assessment information into a condensed authentication assessment indicator having an assessment value selected from a plurality of assessment values based on an assessment value definition;
transmitting, by a computer device to a payment processor, the condensed authentication assessment indicator for the transaction;
receiving, by the computer device from the payment processor, a transaction authentication decision based in part on the condensed authentication assessment indicator, wherein the condensed authentication assessment indicator comprises a standard format configured to provide the initial authentication assessment information as quantitative and consistent information or definitions that are interpreted in a same way by the computer device and by the payment processor;
processing or denying the processing of the transaction, by the computer device, based on the transaction authentication decision; and
periodically train the one or more authentication decision rules via a machine learning model using historical transaction data, wherein latency in receiving completed or true authenticity labels from the payment processor for some historical transactions causes the machine learning model to be trained using partially obtained authenticity labels to forecast complete authenticity volume for each score bin.

13. The method of claim 12 , wherein the assessment value corresponds to an authentication category variable of a plurality of authentication category variables associated with the transaction, wherein the authentication category variable and the assessment value identify an initial assessed level of authenticity of the transaction.

14. The method of claim 12 , wherein the assessment value of the condensed authentication assessment indicator comprises a binary value.

15. The

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Manjunath Murali Krishna
• Jia Yuting
• Reinhardt Adam
• Liu Yung-Wen
• Oka Anand Ravindra
• Nanduri Jayaram N M

Classifications

• G06Q20/4016

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

• G06Q20/405

  Establishing or using transaction specific rules · CPC title

• G06F21/552

  involving long-term monitoring or reporting · CPC title

• G06Q20/3674

  involving authentication · CPC title

• G06F21/554

  involving event detection and direct action · CPC title