Ranking recommended search queries
In one embodiment, a method includes receiving, from a client system of a first user of the communication system, an input from the first user to access a card-stack interface, generating a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain and one or more query-filters, wherein each query-filter references one or more objects associated with the communication system, and wherein each card in the card cluster is ranked within the card cluster based on a predicted click-thru rate (CTR) for the card based on one or more user-engagement factors, and sending, to the client system in response to the input from the first user, the card-stack interface for display to the first user, wherein the card-stack interface comprises the card cluster, the cards of the card cluster being ordered based on the rankings associated with the cards.
1. A method comprising, by a computing device of a communication system:
receiving, from a client system of a first user of the communication system, an input from the first user to access a card-stack interface;
generating a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain and one or more query-filters, wherein each query-filter references one or more objects associated with the communication system, and wherein each card in the card cluster is ranked within the card cluster based on a predicted click-thru rate (CTR) for the card based on one or more user-engagement factors; and
sending, to the client system in response to the input from the first user, the card-stack interface for display to the first user, wherein the card-stack interface comprises the card cluster, the cards of the card cluster being ordered based on the rankings associated with the cards.
2. The method of claim 1 , further comprising:
calculating the predicted CTR for each card in the card cluster based on the one or more user-engagement factors.
3. The method of claim 2 , wherein calculating the predicted CTR comprises determining a click-thru behavior of one or more second users with respect to each card, each second user having at least a subset of demographic information in common with demographic information of the first user.
4. The method of claim 2 , wherein calculating the predicted CTR comprises determining whether the first user is a tourist with respect to the current location based on a comparison of the current location with demographic information of the first user.
5. The method of claim 2 , wherein calculating the predicted CTR comprises calculating a card-affinity of the first user with respect to each card based on the current time of day.
6. The method of claim 2 , wherein calculating the predicted CTR comprises calculating a card-affinity of the first user with respect to each card based on an affinity to the query-domain or query-filter of each card.
7. The method of claim 2 , wherein calculating the predicted CTR comprises calculating a card-affinity based on an affinity of one or more second users to the query-domain or query-filter of each card, the second users having at least a subset of demographic information in common with demographic information of the first user.
8. The method of claim 1 , further comprising:
ranking each of the cards in the card cluster based on the predicted CTR.
9. The method of claim 8 , wherein ranking each of the cards in the card cluster is further based on an associated user-interest value associated with each card.
10. The method of claim 8 , wherein ranking each of the cards in the card cluster comprises ranking each query-domain based on a highest predicted CTR of the cards referencing each query-domain.
11. The method of claim 8 , wherein ranking each of the cards in the card cluster comprises ranking each query-domain based on a calculated average predicted CTR value of the cards referencing each query-domain.
12. The method of claim 8 , wherein ranking each of the cards in the card cluster comprises ranking each query-domain based on a calculated weighted average predicted CTR value of the cards referencing each query-domain.
13. The method of claim 8 , wherein ranking each of the cards in the card cluster comprises calculating a card-affinity of each card relative to an inferred intent of the first user.
14. The method of claim 1 , further comprising:
displaying, at the client system, a subsequent card in the card cluster to the first user in response to detecting an input from the first user corresponding to a swipe of a previously displayed card, the subsequent card having a same query-domain and one or more different query-filters as the previously displayed card.
15. The method of claim 1 , wherein the card-stack interface is displayed on a page currently accessed by the first user.
16. The method of claim 1 , wherein the card-stack interface is displayed on a user interface of a native application installed on the client system that is associated with the communication system.
17. The method of claim 1 , wherein the card cluster is vertically displayed within the card-stack interface, and wherein each displayed card references a different query-domain.
18. The method of claim 1 , further comprising:
accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each of the edges between two of the nodes representing a single degree of separation between them, the nodes comprising:
a first node corresponding to the first user; and
a plurality of second nodes corresponding to a plurality of objects associated with the communication system, respectively,
wherein each query-filter references one or more nodes of the plurality of nodes or one or more edges of the plurality of edges.
19. One or more computer-readable non-transitory storage media embodying software that is operable when executed by a communication system to:
receive, from a client system of a first user of the communication system, an input from the first user to access a card-stack interface;
generate a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain and one or more query-filters, wherein each query-filter references one or more objects associated with the communication system, and wherein each card in the card cluster is ranked within the card cluster based on a predicted click-thru rate (CTR) for the card based on one or more user-engagement factors; and
send, to the client system in response to the input from the first user, the card-stack interface for display to the first user, wherein the card-stack interface comprises the card cluster, the cards of the card cluster being ordered based on the rankings associated with the cards.
20. A communication system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
receive, from a client system of a first user of the communication system, an input from the first user to access a card-stack interface;
generate a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain and one or more query-filters, wherein each query-filter references one or more objects associated with the communication system, and wherein each card in the card cluster is ranked within the card cluster based on a predicted click-thru rate (CTR) for the card based on one or more user-engagement factors; and
send, to the client system in response to the input from the first user, the card-stack interface for display to the first user, wherein the card-stack interface comprises the card cluster, the cards of the card cluster being ordered based on the rankings associated with the cards.