Identification of location-tracked audiences
Disclosed herein identifies audiences of mobile devices that behave a like a seed group of devices. That is, the behave alike group are those devices that move in similar patterns and visit the similar locations with a similar frequency as the devices of the seed group. Similarity is based on correlative similarity in having visited matching categories of location styles identified via mapping data (e.g., devices that visit national parks at a similar frequency). Correlative similarity is performed using a machine learning model trained via a follow the regularized leader proximal.
1. A method of identifying users of mobile devices of a population that are similar to a seed group of users of mobile devices, comprising:
generating device behavior profiles associated with a population of mobile devices, wherein the device behavior profiles include location data of the population of mobile devices over a time period on multiple occasions, the location data including a plurality of coordinates attributed to addresses visited by each respective mobile device of the population of mobile devices;
assigning the addresses visited by each respective mobile device into categories based on a purpose of structures at each given address; and
identifying a subset of the population of mobile devices that are correlatively similar to a seed group of mobile devices based on a relationship to the categories assigned to locations visited by each respective device.
2. The method of claim 1 , further comprising:
generating the seed group from the behavior profiles of the population of mobile devices based on a search query, wherein the query is based on a filterable attribute of device behavior profiles.
3. The method of claim 2 , wherein filterable attributes include any of:
whether the device owner is married;
flagged interests of the device owner from a social media profile;
registered political party of the device owner;
the household income of income the device owner;
the economic net worth of the device owner;
the workplace location of the device owner;
the household location of the device owner;
the category of the device owner's workplace;
the device's last seen date of location data;
categories of locations visited by the device;
distinct commercial businesses visited by the device; or
the number of visits to any particular location by the device.
4. The method of claim 1 , wherein the relationship is based on having visited matching categories of locations.
5. The method of claim 4 , wherein the relationship is further based on having visited matching sub-categories of locations.
6. The method of claim 4 , wherein the relationship is further based on recency of visits to matching categories of locations.
7. The method of claim 4 , wherein the relationship is further based on a number of visits to matching categories of locations.
8. The method of claim 1 , wherein the relationship is based on having visited a same exact location.
9. The method of claim 1 , wherein correlative similarity is further based on matching demographic characteristics between the device behavior profiles of the population of mobile devices and the seed group of mobile devices.
10. The method of claim 1 , where the correlative similarity of the seed group is compared against a filtered subset of the population of mobile devices, the filtered subset of the population of mobile devices is based on any combination of:
geographic filters applied to the population of mobile devices;
social network relationship to the seed group filter applied to the population of mobile devices;
socioeconomic filters applied to the population of mobile devices;
recency of location data filter applied to the population of mobile devices; or
conversion of marketing campaign filter applied to the population of mobile devices.
11. A system of identifying users of mobile devices of a population that behave similarly to a seed group of users of mobile devices, comprising:
a memory including a plurality of device behavior profiles associated with a population of mobile devices, wherein the device behavior profiles include location data of the population of mobile devices over a time period on multiple occasions, the location data including a plurality of coordinates attributed to addresses visited by each respective mobile device of the population of mobile devices, wherein the plurality of device behavior profiles include assignment of the addresses visited by each respective mobile device into categories based on a purpose of structures at each given address; and
a trained machine learning model that identifies a subset of the population of mobile devices that are correlatively similar to a seed group of mobile devices based on a relationship to the categories assigned to locations visited by each respective device.
12. The system of claim 11 , further including:
a processor enabled search engine that is configured to generate the seed group from the behavior profiles of the population of mobile devices based on a search query, wherein the query is based on a filterable attribute of device behavior profiles.
13. The system of claim 12 , wherein filterable attributes include any of:
whether the device owner is married;
the household income of income the device owner;
the economic net worth of the device owner;
the workplace location of the device owner;
the household location of the device owner;
the category of the device owner's workplace;
the device's last seen date of location data;
categories of locations visited by the device;
distinct commercial businesses visited by the device; or
the number of visits to any particular location by the device.
14. The system of claim 11 , wherein the relationship is based on having visited matching categories of locations.
15. The system of claim 14 , wherein the relationship is further based on having visited matching sub-categories of locations.
16. The system of claim 14 , wherein the relationship is further based on recency of visits to matching categories of locations.
17. The system of claim 14 , wherein the relationship is further based on a number of visits to matching categories of locations.
18. The system of claim 11 , wherein the relationship is based on having visited a same exact location.
19. A computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to perform a process comprising:
generating device behavior profiles associated with a population of mobile devices, wherein the device behavior profiles include location data of the population of mobile devices over a time period on multiple occasions, the location data including a plurality of coordinates attributed to addresses visited by each respective mobile device of the population of mobile devices;
assigning the addresses visited by each respective mobile device into categories based on a purpose of structures at each given address; and
identifying a subset of the population of mobile devices that are correlatively similar to a seed group of mobile devices based on a relationship to the categories assigned to locations visited by each respective device.
20. The computer-readable storage medium of claim 19 , further comprising:
generating the seed group from the behavior profiles of the population of mobile devices based on a search query, wherein the query is based on a filterable attribute of device behavior profiles.
21. The computer-readable storage medium of claim 19 , wherein correlative similarity is further based on matching demographic characteristics between the device behavior profiles of the population of mobile devices and the seed group of mobile devices.
22. The computer-readable storage medium of claim 19 , where the correlative similarity of the seed group is compared against a filtered subset of the population of mobile devices, the filtered subset of the population of mobile devices is based on any combination of:
geographic filters applied to the population of mobile devices;
social network relationship to the seed group filter applied to the population of mobile devices;
socioeconomic filters applied to the population of mobile devices;
recency of location data filter applied to the population of mobile devices; or
conversion of marketing campaign filter applied to the population of mobile devices.