Dynamic model-based access right predictions
Systems and methods may use models to generate predictions of specific access rights for users. Further, systems and methods may generate the predictions in an environment in which the availability of the specific access rights change frequently. The access rights, predicted using embodiments described herein, may be both available and associated with user affinities. An interface associated with the primary load management system may be configured to display the predicted access rights for a user operating a user device.
1. A computer-implemented method, comprising:
storing, at a data store associated with a primary load management system, a plurality of electronic tickets, each electronic ticket of the plurality of electronic tickets being associated with a unique code that enables access to a venue during a defined time period, each electronic ticket of the plurality of electronic tickets being assignable to a user, the user being associated with a user device, and one or more electronic tickets of the plurality of electronic tickets being unassigned;
receiving, at the primary load management system, a communication from the user device, the communication corresponding to a request to recommend an electronic ticket;
querying, by the primary load management system, the data store for a real-time state of availability of electronic tickets, the real-time state of availability of electronic tickets representing a set of unassigned electronic tickets;
accessing, by the primary load management system, one or more user data sources associated with the user device, each of the one or more user data sources including a user attribute that characterizes the user or the user device;
generating a first structured data set including user data retrieved from the one or more user data sources;
accessing, by the primary load management system, one or more event data sources, each event data source of the one or more event data sources storing event data representing one or more events, the event data including an event attribute that characterizes an event;
generating a second structured data set including at least a portion of the event data retrieved from the one or more event data sources, the portion of the event data corresponding to a particular event of the one or more events;
generating, by the primary load management system, a model for predicting which unassigned electronic tickets to present to the user device in response to the request included in the received communication, the generation of the model using each of the first structured data set and the second structured data set;
determining a parameter for the particular event that corresponds to the portion of the event data associated with the second structured data set, the parameter representing an affinity to the particular event;
generating, using the model, an event prediction based at least in part on the determined parameter for the particular event that corresponds to the portion of the event data, the event prediction including at least one unassigned electronic ticket to the particular event that corresponds to the portion of the event data associated with the second structured data set; and
displaying, at the user device, the event prediction, the displayed event prediction enabling the user device to request assignment of the at least one unassigned electronic ticket to the particular event.
2. The computer-implemented method of claim 1 , wherein the first structured data set includes a vector, wherein the vector includes one or more items of user data, and wherein each item of user data is based on a user attribute associated with the user device.
3. The computer-implemented method of claim 1 , wherein the second structured data set includes a vector, wherein the vector includes one or more items of the event data, and wherein each item of the event data is based on an event attribute.
4. The computer-implemented method of claim 1 , wherein the parameter is determined by performing a dot product between the first structured data set and the second structured data set.
5. The computer-implemented method of claim 1 , wherein the second structured data set includes a vector with one or more elements, wherein each element of the vector includes a particular event attribute associated with the particular event.
6. The computer-implemented method of claim 1 , wherein the second structured data set includes a vector with one or more elements, wherein each element of the vector includes a previous indication of an affinity initiated by a user associated with the user device, and wherein the previous indication of the affinity is associated with the particular event.
7. The computer-implemented method of claim 6 , wherein the previous indication of affinity initiated by the user includes at least one of a previous assignment to an electronic ticket to the particular event and an indication of affinity retrieved from a social media network.
8. A system, comprising:
one or more data processors; and
a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform operations including:
storing, at a data store associated with a primary load management system, a plurality of electronic tickets, each electronic ticket of the plurality of electronic tickets being associated with a unique code that enables access to a venue during a defined time period, each electronic ticket of the plurality of electronic tickets being assignable to a user, the user being associated with a user device, and one or more electronic tickets of the plurality of electronic tickets being unassigned;
receiving, at the primary load management system, a communication from the user device, the communication corresponding to a request to recommend an electronic ticket;
querying, by the primary load management system, the data store for a real-time state of availability of electronic tickets, the real-time state of availability of electronic tickets representing a set of unassigned electronic tickets;
accessing, by the primary load management system, one or more user data sources associated with the user device, each of the one or more user data sources including a user attribute that characterizes the user or the user device;
generating a first structured data set including user data retrieved from the one or more user data sources;
accessing, by the primary load management system, one or more event data sources, each event data source of the one or more event data sources storing event data representing one or more events, the event data including an event attribute that characterizes an event;
generating a second structured data set including at least a portion of the event data retrieved from the one or more event data sources, the portion of the event data corresponding to a particular event of the one or more events;
generating, by the primary load management system, a model for predicting which unassigned electronic tickets to present to the user device in response to the request included in the received communication, the generation of the model using each of the first structured data set and the second structured data set;
determining a parameter for the particular event that corresponds to the portion of the event data associated with the second structured data set, the parameter representing an affinity to the particular event;
generating, using the model, an event prediction based at least in part on the determined parameter for the particular event that corresponds to the portion of the event data, the event prediction including at least one unassigned electronic ticket to the particular event that corresponds to the portion of the event data associated with the second structured data set; and
displaying, at the user device, the event prediction, the displayed event prediction enabling the user device to request assignment of the at least one unassigned electronic ticket to the particular event.
9. The system of claim 8 , wherein the first structured data set includes a vector, wherein the vector includes one or more items of user data, and wherein each item of user data is based on a user attribute associated with the user device.
10. The system of claim 8 , wherein the second structured data set includes a vector, wherein the vector includes one or more items of the event data, and wherein each item of the event data is based on an event attribute.
11. The system of claim 8 , wherein the parameter is determined by performing a dot product between the first structured data set and the second structured data set.
12. The system of claim 8 , wherein the second structured data set includes a vector with one or more elements, wherein each element of the vector includes a particular event attribute associated with the particular event.
13. The system of claim 8 , wherein the second structured data set includes a vector with one or more elements, wherein each element of the vector includes a previous indication of an affinity initiated by a user associated with the user device, and wherein the previous indication of the affinity is associated with the particular event.
14. The system of claim 13 , wherein the previous indication of affinity initiated by the user includes at least one of a previous assignment to an electronic ticket to the particular event and an indication of affinity retrieved from a social media network.
15. A non-transitory machine-readable storage medium storing instructions which, when executed on a processor, cause the processor to perform operations including:
storing, at a data store associated with a primary load management system, a plurality of electronic tickets, each electronic ticket of the plurality of electronic tickets being associated with a unique code that enables access to a venue during a defined time period, each electronic ticket of the plurality of electronic tickets being assignable to a user, the user being associated with a user device, and one or more electronic tickets of the plurality of electronic tickets being unassigned;
receiving, at the primary load management system, a communication from the user device, the communication corresponding to a request to recommend an electronic ticket;
querying, by the primary load management system, the data store for a real-time state of availability of electronic tickets, the real-time state of availability of electronic tickets representing a set of unassigned electronic tickets;
accessing, by the primary load management system, one or more user data sources associated with the user device, each of the one or more user data sources including a user attribute that characterizes the user or the user device;
generating a first structured data set including user data retrieved from the one or more user data sources;
accessing, by the primary load management system, one or more event data sources, each event data source of the one or more event data sources storing event data representing one or more events, the event data including an event attribute that characterizes an event;
generating a second structured data set including at least a portion of the event data retrieved from the one or more event data sources, the portion of the event data corresponding to a particular event of the one or more events;
generating, by the primary load management system, a model for predicting which unassigned electronic tickets to present to the user device in response to the request included in the received communication, the generation of the model using each of the first structured data set and the second structured data set;
determining a parameter for the particular event that corresponds to the portion of the event data associated with the second structured data set, the parameter representing an affinity to the particular event;
generating, using the model, an event prediction based at least in part on the determined parameter for the particular event that corresponds to the portion of the event data, the event prediction including at least one unassigned electronic ticket to the particular event that corresponds to the portion of the event data associated with the second structured data set; and
displaying, at the user device, the event prediction, the displayed event prediction enabling the user device to request assignment of the at least one unassigned electronic ticket to the particular event.
16. The non-transitory machine-readable storage medium of claim 15 , wherein the first structured data set includes a vector, wherein the vector includes one or more items of user data, and wherein each item of user data is based on a user attribute associated with the user device.
17. The non-transitory machine-readable storage medium of claim 15 , wherein the second structured data set includes a vector, wherein the vector includes one or more items of the event data, and wherein each item of the event data is based on an event attribute.
18. The non-transitory machine-readable storage medium of claim 15 , wherein the parameter is determined by performing a dot product between the first structured data set and the second structured data set.
19. The non-transitory machine-readable storage medium of claim 15 , wherein the second structured data set includes a vector with one or more elements, wherein each element of the vector includes a particular event attribute associated with the particular event.
20. The non-transitory machine-readable storage medium of claim 15 , wherein the second structured data set includes a vector with one or more elements, wherein each element of the vector includes a previous indication of an affinity initiated by a user associated with the user device, and wherein the previous indication of the affinity is associated with the particular event.