Predicting application conversion using eye tracking

1. A computer-implemented method for determining an application experience, comprising:

determining, by a computing device, baseline eye tracking data of a user interacting with an application, the baseline eye tracking data comprising a baseline frequency of pupil dilations of the user;

receiving, at the computing device, real-time eye tracking data of the user interacting with at least a first page of the application, the real-time eye tracking data comprising a real-time frequency of pupil dilations of the user;

determining, by the computing device, based at least on the real-time eye tracking data and the baseline eye tracking data, a current user experience regarding the first page, wherein the current user experience comprises a level of interest with respect to at least a subset of the first page, and wherein the level of interest is determined based on a comparison between the real-time frequency of pupil dilations and the baseline frequency of pupil dilations;

predicting, by the computing device, based on evaluating the current user experience, a user action;

determining, by the computing device, based at least on the predicting, an intervention that changes a likelihood of the user action; and

interacting, by the computing device, with the user according to the intervention.

2. The computer-implemented method of claim 1 , wherein the baseline eye tracking data further comprises one or more of: point of gaze; saccadic eye movement duration; or saccadic eye movement patterns.

3. The computer-implemented method of claim 1 , wherein the intervention is determined by using a model to evaluate the current user experience for the first page and the likelihood of the user action.

4. The computer-implemented method of claim 1 , wherein the current user experience comprises one or more of: excitement, fixation, or fatigue.

5. The computer-implemented method of claim 1 , wherein the intervention comprises at least one of: offering a discount, offering assisted support, offering self-support content, or providing a list of content items.

6. The computer-implemented method of claim 1 , wherein interacting with the user according to the intervention comprises at least one of: a real-time intervention, an off-line intervention, presenting content items on an interface of the user, or altering at least one content item of the interface of the user.

7. The computer-implemented method of claim 1 , wherein the current user experience relates to a particular item on the first page.

8. The computer-implemented method of claim 1 , further comprising:

determining at least one metric comprising one or more of:

a count of user clicks for the first page;

a total amount of time spent by the user on the first page;

an age of the user;

a gender of the user;

an occupation of the user; or

a location of the user; and

evaluating the at least one metric in addition to the current user experience, using a model, to determine the likelihood of the user action.

9. A system for determining an application experience, comprising:

one or more processors; and

a memory comprising instructions that, when executed by the one or more processors, cause the system to:

determine, by a computing device, baseline eye tracking data of a user interacting with an application, the baseline eye tracking data comprising a baseline frequency of pupil dilations of the user;

receive, at the computing device, real-time eye tracking data of the user interacting with at least a first page of the application, the real-time eye tracking data comprising a real-time frequency of pupil dilations of the user;

determine, by the computing device, based at least on the real-time eye tracking data and the baseline eye tracking data, a current user experience regarding the first page, wherein the current user experience comprises a level of interest with respect to at least a subset of the first page, and wherein the level of interest is determined based on a comparison between the real-time frequency of pupil dilations and the baseline frequency of pupil dilations;

predict, by the computing device, based on evaluating the current user experience, a user action;

determine, by the computing device, based at least on the user action that was predicted, an intervention that changes a likelihood of the user action; and

interact, by the computing device, with the user according to the intervention.

10. The system of claim 9 , wherein the baseline eye tracking data further comprises one or more of: point of gaze; saccadic eye movement duration; or saccadic eye movement patterns.

11. The system of claim 9 , wherein the intervention is determined by using a model to evaluate the current user experience for the first page and the likelihood of the user action.

12. The system of claim 9 , wherein the current user experience comprises one or more of: excitement, fixation, or fatigue.

13. The system of claim 9 , wherein the intervention comprises at least one of: offering a discount, offering assisted support, offering self-support content, or providing a list of content items.

14. The system of claim 9 , wherein interacting with the user according to the intervention comprises at least one of: a real-time intervention, an off-line intervention, presenting content items on an interface of the user, or altering at least one content item of the interface of the user.

15. The system of claim 9 , wherein the current user experience comprises relates to a particular item on the first page.

16. The system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause the system to:

determine at least one metric comprising one or more of:

a count of user clicks for the first page;

a total amount of time spent by the user on the first page;

an age of the user;

a gender of the user;

an occupation of the user; or

a location of the user; and

evaluate the at least one metric in addition to the current user experience, using a model, to determine the likelihood of the user action.

17. A computer-implemented method for determining an application experience, comprising:

determining, by a computing device, baseline eye tracking data of a user interacting with an application, the baseline eye tracking data comprising a baseline frequency of pupil dilations of the user;

receiving, at the computing device, real-time eye tracking data of the user interacting with at least a first page of the application, the real-time eye tracking data comprising a real-time frequency of pupil dilations of the user;

determining, by the computing device, based at least on the real-time eye tracking data and the baseline eye tracking data, a current user experience regarding the first page, wherein the current user experience comprises a numerical score indicating a level of interest with respect to at least a subset of the first page, and wherein the numerical score is determined based on a comparison between the real-time frequency of pupil dilations and the baseline frequency of pupil dilations;

predicting, by the computing device, based on evaluating the current user experience, a user action;

determining, by the computing device, based at least on the predicting, a type of intervention that changes a likelihood of the user action; and

interacting, by the computing device, with the user according to the type of intervention.

18. The computer-implemented method of claim 17 , wherein the baseline eye tracking data further comprises one or more of: point of gaze; saccadic eye movement duration; or saccadic eye movement patterns.

19. The computer-implemented method of claim 17 , wherein the type of intervention is determined by using a model to evaluate the current user experience for the first page and the likelihood of the user action.

20. The computer-implemented method of claim 17 , wherein the current user experience comprises one or more of: excitement, fixation, or fatigue.