System and method for increasing online conversion rate of potential users

Patent metadata

Field	Value
Publication number	US-9947028-B1
Application number	US-201414192185-A
Country	US
Kind code	B1
Filing date	Feb 27, 2014
Priority date	Feb 27, 2014
Publication date	Apr 17, 2018
Grant date	Apr 17, 2018

Abstract

A computer-implemented method of increasing the online conversion rate of potential users to a computer-hosted service is described. The method includes a computing device receiving a browser request from a potential user, the computing device receiving user-specific data as part of the browser request. The computing device inputs the user-specific data into a conversion model executed by the computing device and outputs a conversion score for the potential user based on the model. The computing device sends to the browser a marketing intervention if the conversion score falls below a pre-determined threshold value.

First claim

What is claimed is:

1. A computer-implemented method of increasing an online conversion rate of potential users to a computer-hosted service comprising:
generating, by a processor, a conversion model by:
applying logistic regression to a data set of past users of the computer-hosted service that visited a webpage of the computer-hosted service,
determining attributes corresponding to user-specific data that are statistically significant at predicting a conversion and associated attribute weightings,
determining an intercept value, and
encoding the conversion model having binary logic associated with the statistically significant attributes, the attribute weightings, and the intercept value, in JavaScript;

retrieving, by a computing device of a potential user, the conversion model encoded in the JavaScript when the computing device communicates with the computer-hosted service;
capturing, by the computing device of the potential user, user-specific data from a browser executing on the computing device of the potential user the user-specific data having attributes comprising:
a query length integer value corresponding to a character length of a search engine query executed in a search engine used by the potential user, and
a name of a first landing page for the potential user, the first landing page being a webpage the potential user first landed on and being determined based at least in part on a link the potential user clicked on in a previous location;

inputting by the computing device of the potential user the captured user-specific data into the conversion model
executing, by the computing device of the potential user, the received conversion model by at least:
executing rules that assign a binary attribute value to each applicable attribute of the user-specific data other than the query length
for each applicable attribute other than the query length, multiplying a respective binary attribute value with an associated attribute weighting,
multiplying the query length integer value with an associated attribute weighting, and
generating a conversion score for the potential user by summing the computed values resulting from each multiplication and the intercept value;

outputting, by the computing device of the potential user, the conversion score for the potential user;
determining, by the computing device of the potential user, that the conversion score is below a predetermined threshold value; and
presenting, by the computing device of the potential user, an electronic communication to the potential user responsive to the determination that the conversion score is below the pre-determined threshold value.

2. The computer-implemented method of claim 1 , wherein the computing device communicates with the computer-hosted service via a browser running on the computing device.

3. The computer-implemented method of claim 1 , wherein the user-specific data comprises browser navigation data.

4. The computer-implemented method of claim 1 , wherein the user-specific data comprises user behavioral data.

5. The computer-implemented method of claim 1 , wherein the user-specific data comprises IP address data.

6. The computer-implemented method of claim 1 , wherein the user-specific data comprises browser search data.

7. The computer-implemented method of claim 1 , wherein the user-specific data comprises one or more of browser type data, operating system data, and computer hardware data.

8. The computer-implemented method of claim 1 , wherein the user-specific data comprises cookie data.

9. The computer-implemented method of claim 1 , wherein the electronic communication is executable by a browser of the computing device to open a chat dialog box presented through a display of the computing device.

10. The computer-implemented method of claim 1 , wherein the electronic communication is executable by a browser of the computing device to present a modified web page through a display of the computing device.

11. The computer-implemented method of claim 1 , wherein the electronic communication is executable by a browser of the computing device to present a visual discount indicia through a display of the computing device.

12. The computer-implemented method of claim 1 , wherein the electronic communication is executable by a browser of the computing device to present a priority queuing offer through a display of the computing device.

13. The computer-implemented method of claim 1 , wherein the electronic communication is executable by a browser of the computing device to redirect the potential user to a super-user session.

14. The computer-implemented method of claim 1 , wherein the computer-hosted service comprises an on-line tax return preparation application.

15. The computer-implemented method of claim 1 , wherein the computer-hosted service comprises an on-line question and answer service.

16. The computer-implemented method of claim 15 , wherein the on-line question and answer service comprises an on-line tax question and answer service.

17. The computer-implemented method of claim 1 , further comprising the computer-hosted service assigning an identification number to the potential user and storing the identification number in a database utilized by the computer-hosting service.

18. A system for increasing an online conversion rate of potential users to a computer-hosted service comprising:
a computing device of a potential user comprising;
a memory storing instructions,
a processor communicatively coupled to the memory, wherein the instructions, when executed by the processor, cause the processor to;
retrieve JavaScript encoding a conversion model through a network when the computing device communicates with the computer-hosted service, wherein the conversion model is generated by a processor external to the computing device of the potential user by:
applying logistic regression to a data set of past users of the computer-hosted service that visited a webpage of the computer-hosted service,
determining attributes corresponding to user-specific data that are statistically significant at predicting a conversion and associated attribute weightings,
determining an intercept value, and
encoding the conversion model having binary logic associated with the statistically significant attributes, the attribute weightings, and the intercept value, in the JavaScript;

capture user-specific data from a browser executing on the computing device of a potential user, the user-specific data having attributes comprising:
a query length corresponding to a character length of a search engine query executed in a search engine used by the potential user, and
a name of a first landing page for the potential user, the first landing page being a webpage the potential user first landed on determined based at least in part on a link the potential user clicked on in a previous location; and

input the captured user-specific data into the conversion model encoded in the JavaScript
execute the received conversion model by at least:
executing rules that assign a binary attribute value to each applicable attribute of the user-specific data other than the query length
for each applicable attribute other than the query length, multiplying a respective binary attribute value with an associated attribute weighting,
multiplying the query length integer value with an associated attribute weighting, and
generating a conversion score for the potential user by summing the computed values resulting from each multiplication and the intercept value;

output the

Assignees

• Intuit Inc

Inventors

• Podgorny Igor A
• Bartolome Warren E
• Goodyear Todd

Classifications

• G06Q30/0242 Primary

  Determining effectiveness of advertisements · CPC title

• G06Q30/0269 Primary

  based on user profile or attribute · CPC title

• G06Q40/123

  Tax preparation or submission · CPC title