Content recommendation based on a system prediction and user behavior
Systems and methods for generating a content item based on a difference between a user confidence score and a confidence score are disclosed. For example, a system generates for output a first content item. While the first content item is being outputted, the system receives user data via sensors of a device. The system determines a user confidence score based on the user data and metadata of the first content item. The user confidence score indicates a user's perceived probability of an event occurring in the future. The system calculates a prediction score which estimates the likelihood of the event occurring in the future. In response to determining that the difference between the user confidence score and the prediction score exceeds a threshold, the system selects a second content item related to the event and generates for output a recommendation comprising an identifier of the second content item.
1. A method comprising:
generating for output a first content item on a device;
while the first content item is being outputted, receiving user data via one or more sensors of the device;
determining a user confidence score based on the user data and metadata of the first content item, the user confidence score indicating user's perceived probability of an event occurring in the future;
calculating a prediction score which estimates the likelihood of the event occurring in the future;
in response to determining that the difference between the user confidence score and the prediction score exceeds a threshold:
selecting a second content item related to the event; and
generating for output a recommendation comprising an identifier of the second content item.
2. The method of claim 1 , further comprising:
determining a user engagement score based on the user data received via one or more sensors, the user engagement score representing a degree of user engagement with the first content item.
3. The method of claim 1 , wherein the first content is a depiction of a sport event, the method further comprising:
generating a probabilistic model that predicts the likelihood of a first team winning in the sport event based on training data, wherein the prediction score is trained based on the probabilistic model using one or more machine learning algorithms.
4. The method of claim 3 , wherein the user's perceived probability of the event occurring in the future indicates a user's perceived winning chance of the first team over a second team in the sport event.
5. The method of claim 3 , wherein the second content item comprises a depiction of an object related to the sport event.
6. The method of claim 3 , wherein the selecting a second content item related to the event comprises:
accessing a database of content items comprising at least one of data related to the event, data related to the first team, or data related to the second team; and
wherein selecting the second content item is based on data retrieved from the database of content items.
7. The method of claim 1 , further comprising:
determining a time of when the user confidence score is determined;
wherein generating for output the recommendation is based on the determining that the time is within a threshold value.
8. The method of claim 1 , further comprising:
in response to determining that the difference between the user confidence score and the prediction score does not exceed the threshold:
selecting a third content item different from the second content item; and
generating for output a recommendation comprising an identifier of the third content item.
9. The method of claim 1 , further comprising:
receiving user input selecting the identifier of the second content item; and
presenting a first set of user-selectable options associated with the second content item for display.
10. The method of claim 1 , further comprising:
without receiving user input selecting the identifier of the second content item, selecting a fourth content item different from the second content item; and
generating for output a recommendation comprising an identifier of the fourth content item.
11. A system comprising:
control circuitry configured to:
generate for output a first content item on a device;
input/output circuitry configured to:
while the first content item is being outputted, receive user data via one or more sensors of the device;
wherein the control circuitry is further configured to:
determine a user confidence score based on the user data and metadata of the first content item, the user confidence score indicating user's perceived probability of an event occurring in the future;
calculate a prediction score which estimates the likelihood of the event occurring in the future;
in response to determining that the difference between the user confidence score and the prediction score exceeds a threshold:
select a second content item related to the event; and
generate for output a recommendation comprising an identifier of the second content item.
12. The system of claim 11 , wherein the control circuitry is further configured to:
determine a user engagement score based on the user data received via one or more sensors, the user engagement score representing a degree of user engagement with the first content item.
13. The system of claim 11 , wherein the first content is a depiction of a sport event, wherein the control circuitry is configured to:
generate a probabilistic model that predicts the likelihood of a first team winning in the sport event based on training data, wherein the prediction score is trained based on the probabilistic model using one or more machine learning algorithms.
14. The system of claim 13 , wherein the user's perceived probability of the event occurring in the future indicates a user's perceived winning chance of the first team over a second team in the sport event.
15. The system of claim 13 , wherein the second content item comprises a depiction of an object related to the sport event.
16. The system of claim 13 , wherein the control circuitry, when selecting a second content item related to the event, is configured to:
access a database of content items comprising at least one of data related to the event, data related to the first team, or data related to the second team; and
wherein selecting the second content item is based on data retrieved from the database of content items.
17. The system of claim 11 , wherein the control circuitry is further configured to:
determine a time of when the user confidence score is determined;
wherein generating for output the recommendation is based on the determining that the time is within a threshold value.
18. The system of claim 11 , wherein the control circuitry is further configured to:
in response to determining that the difference between the user confidence score and the prediction score does not exceed the threshold:
select a third content item different from the second content item; and
generate for output a recommendation comprising an identifier of the third content item.
19. The system of claim 11 , wherein the control circuitry is further configured to:
receive user input selecting the identifier of the second content item; and
present a first set of user-selectable options associated with the second content item for display.
20. The system of claim 11 , wherein the control circuitry is further configured to:
without receiving user input selecting the identifier of the second content item, select a fourth content item different from the second content item; and
generate for output a recommendation comprising an identifier of the fourth content item.