Computer implemented methods and apparatus for recommending events
Disclosed are methods, apparatus, systems, and computer-readable storage media for recommending an event to a user. In some implementations, one or more servers receive information identifying a plurality of events. The one or more servers store data of the plurality of events in a first one or more data tables having an action field, an intent field, and a user field, and analyze the data of the first one or more data tables to generate one or more pairs, each pair including information identifying a set of events and a target event. The one or more servers may calculate a similarity score for each of the one or more pairs and store the respective similarity score in a second one or more data tables having a set field, a target event field, and a similarity score field.
1. A system for recommending an action to a user, the system comprising:
a server system including one or more hardware processors, the one or more hardware processors configured to:
monitor actions performed in a database system by a group of one or more users;
identify a first action performed by the users associated with a first item followed by a second action by the group of users associated with a second item;
determine a frequency of the users performing the first action followed by the second action;
monitor actions of a current user;
identify an action of the current user similar to the first action by the group of users; and
display on a user interface of a computing device a recommendation of the second item to the current user based on the frequency of the first action followed by the second action.
2. The system of claim 1 , the hardware processors further configured to:
display on the user interface a message to the current user indicating other users performing the first action have also performed the second action.
3. The system of claim 1 , wherein the first action is associated with viewing the first item and the second action is associated with buying the second item.
4. The system of claim 1 , the hardware processors further configured to arrange or rearrange data on the user interface to highlight the second item.
5. The system of claim 1 , the hardware processors further configured to display on the user interface, a link to the second item.
6. The system of claim 5 , the hardware processors further configured to display the link at the top of a list of links to associated items.
7. The system of claim 1 , the hardware processors further configured to:
determine action identifiers for each of the first and second action,
determine item identifiers for each of the first and second items,
determine user identifiers for each of the users generating the first and second actions;
store the action identifiers in an action field of a database table,
store the item identifiers in an item field of the database table; and
store the user identifiers in a user field of the database table.
8. The system of claim 7 , the hardware processors further configured to use the action identifiers, item identifiers, and user identifiers to identify the second action and second item associated with the first action and first item.
9. The system of claim 1 , the hardware processors further configured to identify the second action performed within a designated time period following the first action.
10. A method for using a database system to provide recommendations to a user of a computing device, comprising:
identifying, by one or more hardware processors in the database system, sequences of events performed by the users;
determining, by the one or more hardware processors in the database system, frequencies for the sequences of events;
identifying, by the one or more hardware processors in the database system, in the sequences of the events a first action followed by an associated second action;
identifying, by the one or more hardware processors in the database system, an action of a current user matching the first action in one of the sequences of events; and
displaying, by the one or more hardware processors in the database system, on a user interface a message to the current user identifying the second action based on a frequency of the first action followed by the second action.
11. The method of claim 10 , further comprising:
displaying, by the one or more hardware processors in the database system, on the user interface of the computing device, a message to the current user indicating other users performing the first action have also performed the associated second action.
12. The method of claim 10 , further comprising:
identifying, by the one or more hardware processors in the database system, a first item associated with the first action and a second item associated with the second action and
displaying in the message to the current user that other users performing the first action associated with the first item have also performed the second action associated with the second item.
13. The method of claim 12 , wherein the first action views the first item and the second action buys the second item.
14. The method of claim 12 , further comprising:
displaying, by the one or more hardware processors in the database system, on the user interface of the computing device, a link to the second item.
15. The method of claim 12 , further comprising:
determining, by the one or more hardware processors in the database system, action identifiers for the first and second action,
determining, by the one or more hardware processors in the database system, item identifiers for the first item and second item,
determining, by the one or more hardware processors in the database system, user identifiers for the users generating the first and second action;
storing, by the one or more hardware processors in the database system, the action identifiers in an action field of a database table;
storing, by the one or more hardware processors in the database system, the item identifiers in an item field of the database table;
storing, by the one or more hardware processors in the database system, the user identifiers in a user field of the database table; and
using, by the one or more hardware processors in the database system, the stored action identifiers, item identifiers, and user identifiers to identify the second action and second item associated with the first action and first item.
16. A computer system comprising program code to be executed by at least one processor when retrieved from a non-transitory computer-readable storage medium for recommending events, the program code comprising instructions configured to cause the processor to:
identify sequences of the events performed by users;
identify in at least some of the sequences of the events a first action followed by an associated second action;
identify a frequency of the first action followed by the associated second action;
identify the first action in one of the sequences of events matching an action of a current user; and
display on a user interface of a computing device, a message to the current user indicating other users performing the matching first action have also performed the second action based on a frequency of the first action followed by the second action.
17. The computer system of claim 16 , the instructions further configured to cause the processor to:
identify a first item associated with the first action and a second item associated with the second action; and
display on the user interface of the computing device a message to the current user indicating other users performing the first action associated with the first item have also performed the second action associated with the second item.
18. The computer system of claim 16 , wherein the first action views a first item and the second action buys a second item.