Method and system for creating a predictive model for targeting web-page to a surfer
Systems and methods for determining predictive model types are provided. A method may include generating a predictive model for a web page of a web site, wherein the web page includes a configuration defining one or more objects presented with the web page, and wherein each object is associated with a predictive model. The method may include determining one or more predictive model types that are associated with the predictive model, determining one or more performance indicators that correspond to each determined predictive model type, wherein performance indicators represent one or more benefits to a website, selecting a predictive model type of the predictive model out of the one or more predictive model types, wherein the predictive model type is selected based on a performance indicator corresponding to the selected predictive model type, and determining a configuration of the web page using the selected predictive model type of the predictive model.
1. A computer-implemented method, comprising:
receiving an identification of one or more predictive factors associated with a web page, wherein the one or more predictive factors are indicators of user interaction with the webpage;
receiving information corresponding to the one or more predictive factors over time, wherein the information is stored as a control dataset;
training a predictive model, wherein the predictive model summarizes and analyzes trends within the control dataset;
generating a modified webpage by applying the predictive model to content of the webpage; and
continuously updating the modified webpage over a plurality of iterations, wherein each iteration includes:
receiving updated information corresponding to the one or more predictive factors;
comparing the updated information to the control dataset, wherein comparing includes identifying discrepancies and similarities between the updated information and the control dataset;
generating a modified predictive model according to the discrepancies and similarities; and
altering the modified webpage by applying the modified predictive model to the content of the modified webpage, wherein altering the modified webpage generates a subsequently modified webpage.
2. The method of claim 1 , wherein the predictive factors include information associated with one or more responses to one or more objects.
3. The method of claim 1 , wherein the predictive factors include a time of a previous request associated with content of the webpage, a time that the content was last requested, a number of visits to the webpage, a number of times that an object has been presented, or a number of times that the object has been selected.
4. The method of claim 1 , wherein the predictive factors include a receipt time of a response, a uniform resource locator key associated with the response, an internet protocol address, or a type of browser application.
5. The method of claim 1 , wherein the webpage is associated with a mobile application.
6. The method of claim 1 , wherein altering the modified webpage includes applying the predictive model to a layout of the webpage.
7. The method of claim 1 , wherein training the predictive model includes performing a logistic regression or a linear regression.
8. A system, comprising:
a processor; and
a non-transitory computer-readable storage medium containing instructions which when executed on the processor, cause the processor to perform operations including:
receiving an identification of one or more predictive factors associated with a webpage, wherein the one or more predictive factors are indicators of user interaction with the webpage;
receiving information corresponding to the one or more predictive factors over time, wherein the information is stored as a control dataset;
training a predictive model, wherein the first number of events arc associated with a first predictive model summarizes and analyzes trends within the control dataset;
generating a modified webpage by applying the predictive model to content of the webpage; and
continuously updating the modified webpage over a plurality of iterations, wherein each iteration includes:
receiving updated information corresponding to the one or more predictive factors;
comparing the updated information to the control dataset, wherein comparing includes identifying discrepancies and similarities between the updated information and the control dataset;
generating a modified predictive model according to the discrepancies and similarities; and
altering the modified webpage by applying the modified predictive model to the content of the modified webpage, wherein altering the modified webpage generates a subsequently modified webpage.
9. The system of claim 8 , wherein the predictive factors include information associated with one or more responses to one or more objects.
10. The system of claim 8 , wherein the predictive factors include a time of a previous request associated with content of the webpage, a time that the content was last requested, a number of visits to the webpage, a number of times that an object has been presented, or a number of times that the object has been selected.
11. The system of claim 8 , wherein the predictive factors include a receipt time of a response, a uniform resource locator key associated with the response, an internet protocol address, or a type of browser application.
12. The system of claim 8 , wherein the webpage is associated with a mobile application.
13. The system of claim 8 , wherein altering the modified webpage includes applying the predictive model to a layout of the webpage.
14. The system of claim 8 , wherein training the predictive model includes performing a logistic regression or a linear regression.
15. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a data processing apparatus to:
receive an identification of one or more predictive factors associated with a webpage, wherein the one or more predictive factors are indicators of user interaction with the webpage;
receive information corresponding to the one or more predictive factors over time, wherein the information is stored as a control dataset;
train a predictive model, wherein the first number of events are associated with a first predictive model summarizes and analyzes trends within the control dataset;
generate a modified webpage by applying the predictive model to content of the webpage; and
continuously update the modified webpage over a plurality of iterations, wherein each configuration iteration includes:
receive updated information corresponding to the one or more predictive factors;
compare the updated information to the control dataset, wherein comparing includes identifying discrepancies and similarities between the updated information and the control dataset;
generate a modified predictive model according to the discrepancies and similarities; and
alter the modified webpage by applying the modified predictive model to the content of the modified webpage, wherein altering the modified webpage generates a subsequently modified webpage.
16. The computer-program product of claim 15 , wherein the predictive factors include information associated with one or more responses to one or more objects.
17. The computer-program product of claim 15 , wherein the predictive factors inclue a time of a previous request associated with content of the webpage, a time that the content was last requested, a number of visits to the webpage, a number of times that an object has been presented, or a number of times that the object has been selected.
18. The computer-program product of claim 15 , wherein the predictive factors include a receipt time of a response, a uniform resource locator key associated with the response, an internet protocol address, or a type of browser application.
19. The computer-program product of claim 15 , wherein the webpage is associated with a mobile application.
20. The computer-program product of claim 15 , wherein altering the modified webpage includes applying the predictive model to a layout of the webpage.
21. The computer-program product of claim 15 , wherein training the predictive model includes performing a logistic regression or a linear regression.