Systems and methods for providing contextual recommendations for pages based on user intent
Systems, methods, and non-transitory computer readable media can determine one or more actions that a user is likely to take on a page associated with a social networking system, based on one or more first machine learning models. One or more card types that correspond to the one or more actions can be ranked based on a second machine learning model. One or more cards can be generated based on the ranked card types, and each card can include a recommended action associated with the page.
1. A computer-implemented method comprising:
predicting, by a computing system, one or more actions that a user may take while accessing a page associated with an entity of a plurality of entities represented on a social networking system based on one or more first machine learning models, wherein the user and the entity are different members of the social networking system and the one or more first machine learning models output scores indicating probabilities of the user taking the one or more actions on the page;
in response to the predicting, ranking, by the computing system, one or more card types that correspond to the one or more actions based on a second machine learning model, wherein the second machine learning model is trained based at least in part on the scores; and
generating, by the computing system, on the page one or more cards based on the ranked card types, each card including a recommended action to be taken on the page.
2. The computer-implemented method of claim 1 , further comprising:
providing, by the computing system, the one or more cards for display to the user through the page.
3. The computer-implemented method of claim 1 , further comprising:
providing, by the computing system, the one or more cards for display to the user through a feed of the user.
4. The computer-implemented method of claim 1 , wherein the one or more first machine learning models are trained to predict a probability of users taking particular actions on pages.
5. The computer-implemented method of claim 1 , wherein the second machine learning model is trained to predict a probability of users engaging with cards of particular card types.
6. The computer-implemented method of claim 1 , wherein a card includes a header, content, a footer, personalized data, and a button associated with a recommended action.
7. The computer-implemented method of claim 6 , wherein the content includes at least one of an image, a video, text, a link, a map, a preview, a review, or a portion of a review.
8. The computer-implemented method of claim 1 , wherein the one or more first machine learning models are trained based on features including one or more of: user attributes, page attributes, attributes associated with interactions between users and pages, or attributes associated with interactions between users and page categories.
9. The computer-implemented method of claim 1 , wherein the second machine learning model is trained based on features including one or more of: click through rates for cards, click through rates for card types, user attributes, page attributes, attributes associated with interactions between users and pages, or attributes associated with interactions between users and page categories.
10. The computer-implemented method of claim 1 , wherein the one or more actions are indicative of an intent of the user for visiting the page.
11. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
predicting one or more actions that a user may take on a page associated with an entity of a plurality of entities represented on a social networking system based on one or more first machine learning models, wherein the user and the entity are different members of the social networking system and the one or more first machine learning models output scores indicating probabilities of the user taking the one or more actions on the page;
in response to the predicting, ranking one or more card types that correspond to the one or more actions based on a second machine learning model, wherein the second machine learning model is trained based at least in part on the scores; and
generating on the page one or more cards based on the ranked card types, each card including a recommended action to be taken on the page.
12. The system of claim 11 , wherein the one or more first machine learning models are trained to predict a probability of users taking particular actions on pages.
13. The system of claim 11 , wherein the second machine learning model is trained to predict a probability of users engaging with cards of particular card types.
14. The system of claim 11 , wherein a card includes a header, content, a footer, personalized data, and a button associated with a recommended action.
15. The system of claim 11 , wherein the one or more actions are indicative of an intent of the user for visiting the page.
16. A non-transitory computer readable medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
predicting one or more actions that a user may take on a page associated with an entity of a plurality of entities represented on a social networking system based on one or more first machine learning models, wherein the user and the entity are different members of the social networking system and the one or more first machine learning models output scores indicating probabilities of the user taking the one or more actions on the page;
in response to the predicting, ranking one or more card types that correspond to the one or more actions based on a second machine learning model, wherein the second machine learning model is trained based at least in part on the scores; and
generating on the page one or more cards based on the ranked card types, each card including a recommended action to be taken on the page.
17. The non-transitory computer readable medium of claim 16 , wherein the one or more first machine learning models are trained to predict a probability of users taking particular actions on pages.
18. The non-transitory computer readable medium of claim 16 , wherein the second machine learning model is trained to predict a probability of users engaging with cards of particular card types.
19. The non-transitory computer readable medium of claim 16 , wherein a card includes a header, content, a footer, personalized data, and a button associated with a recommended action.
20. The non-transitory computer readable medium of claim 16 , wherein the one or more actions are indicative of an intent of the user for visiting the page.