Adaptive data platforms

Patent metadata

Field	Value
Publication number	US-11086963-B2
Application number	US-201816210845-A
Country	US
Kind code	B2
Filing date	Dec 5, 2018
Priority date	Dec 5, 2018
Publication date	Aug 10, 2021
Grant date	Aug 10, 2021

Abstract

An experimentation platform controls testing of features by an application server. Based on a user identifier, the experimentation platform determines which feature should be provided, and the application server provides the corresponding version of a user interface. If the user behavior data shows that using a tested feature results in an improvement, the tested feature will be adopted. To determine whether or not an improvement is observed, a statistically significant amount of data is gathered. The experimentation platform gathers data regarding user behavior for the feature versions and, in response, adjusts the frequency at which each version is served. Providing the proposed version to an increased percentage of users decreases the total number of page serves required to gather statistically significant data. The experimentation platform may provide an updated projected time to completion of testing based on the changed percentage of users receiving the proposed version.

First claim

What is claimed is:

1. A computer-implemented method for executing a randomized controlled trial, the method comprising:
receiving an identity of an element of a user interface;
receiving an attribute of the element of the user interface;
by one or more processors, automatically determining a first value and a second value for the attribute of the element of the user interface;
automatically generating a first user interface, the first user interface having the attribute of the element set at the first value, the first user interface defining a first test input to the randomized controlled trial;
automatically generating a second user interface, the second user interface having the attribute of the element set at the second value, the second user interface defining a second test input to the randomized controlled trial;
providing the first user interface to a first percentage of users, the first user interface having the attribute of the element set at the first value;
providing the second user interface to a second percentage of users, the second user interface having the attribute of the element set at the second value;
based on interactions with the element in the first user interface, determining a first set of test results;
based on interactions with the element in the second user interface, determining a second set of test results;
based on the first and second sets of test results, automatically adapting the first and second percentages;
providing the first and second user interfaces to the adapted first and second percentages of users;
generating iteratively adapted first and second percentages as additional test results are received; and
providing the first and second user interfaces to the iteratively adapted first and second percentages of users.

2. The method of claim 1 , wherein the attribute of the element is a color of the element.

3. The method of claim 1 , wherein the attribute of the element is text content of the element.

4. The method of claim 1 , wherein the attribute of the element is a location of the element.

5. The method of claim 1 , wherein the user interface is part of a web site.

6. The method of claim 1 , wherein the user interface is displayed on a wearable computer.

7. The method of claim 1 , wherein the user interface is a voice interface.

8. The method of claim 1 , further comprising:
determining an updated amount of time for testing the first user interface and the second user interface based on the adapted first and second percentages.

9. The method of claim 1 , wherein:
interaction with the element in the first user interface causes a further user interface to be presented; and
the interactions with the element in the first user interface are based on input received via the further user interface.

10. The method of claim 1 , further comprising analyzing a first performance of the first user interface and a second performance of the second user interface and presenting a third user interface based on the analyzing.

11. The method of claim 1 , wherein the determining of the first set of test results comprises generating a vector and providing the vector as input to a machine learning system.

12. The method of claim 11 , wherein the vector comprises an indication of whether an item was sold.

13. The method of claim 11 , wherein the vector comprises an indication of whether fraud occurred.

14. The method of claim 11 , wherein elements of the vector are automatically selected based on the received identity of the user interface.

15. A system comprising:
a memory that stores instructions; and
one or more processors configured by the instructions to perform operations comprising:
receiving an identity of an element of a user interface;
receiving an attribute of the element of the user interface;
automatically determining a first value and a second value for the attribute of the element of the user interface;
automatically generating a first user interface, the first user interface having the attribute of the element set at the first value, the first user interface defining a first test input to a randomized controlled trial;
automatically generating a second user interface, the second user interface having the attribute of the element set at the second value, the second user interface defining a second test input to the randomized controlled trial;
providing the first user interface to a first percentage of users, the first user interface having the attribute of the element set at the first value;
providing the second user interface to a second percentage of users, the second user interface having the attribute of the element set at the second value;
based on interactions with the element in the first user interface, determining a first set of test results;
based on interactions with the element in the second user interface, determining a second set of test results;
based on the first and second sets of test results, automatically adapting the first and second percentages;
providing the first and second user interfaces to the adapted first and second percentages of users;
generating iteratively adapted first and second percentages as additional test results are received; and
providing the first and second user interfaces to the iteratively adapted first and second percentages of users.

16. The system of claim 15 , wherein the attribute of the element is a color of the element.

17. The system of claim 15 , wherein the attribute of the element is text content of the element.

18. A non-transitory machine-storage medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving an identity of an element of a user interface;
receiving an attribute of the element of the user interface;
automatically determining a first value and a second value for the attribute of the element of the user interface;
automatically generating a first user interface, the first user interface having the attribute of the element set at the first value, the first user interface defining a first test input to a randomized controlled trial;
automatically generating a second user interface, the second user interface having the attribute of the element set at the second value, the second user interface defining a second test input to the randomized controlled trial;
providing the first user interface to a first percentage of users, the first user interface having the attribute of the element set at the first value;
providing the second user interface to a second percentage of users, the second user interface having the attribute of the element set at the second value;
based on interactions with the element in the first user interface, determining a first set of test results;
based on interactions with the element in the second user interface, determining a second set of test results;
based on the first and second sets of test results, automatically adapting the first and second percentages;
providing the first and second user interfaces to the adapted first and second percentages of users;
generating iteratively adapted first and second percentages as additional test results are received; and
providing the first and second user interfaces to the iteratively adapted first and second percentages of users.

19. The non-transitory machine-storage medium of claim 18 , wherein the attribute of the element is a color of the element.

20. The non-transitory machine-storage medium

Assignees

• Ebay Inc

Inventors

• Vasthimal Deepak Kumar
• Srirama Pavan Kumar
• Akkinapalli Arun Kumar

Classifications

• G06Q30/0641

  utilising user interfaces specially adapted for shopping · CPC title

• G06Q30/0242

  Determining effectiveness of advertisements · CPC title

• G06F11/3447

  Performance evaluation by modeling · CPC title

• G06F2201/88

  Monitoring involving counting · CPC title

• G06N20/00

  Machine learning · CPC title