Correlating user device attribute groups

A method for data processing at a database server, comprising:

• receiving, from a first data source, a first data set for a first set of user devices;
• identifying, within the first set of user devices, a first subset of user devices from the first set of user devices characterized by a first set of attributes;
• receiving, from a second data source different from the first data source, a second data set for a second set of user devices characterized by a second set of attributes;
• identifying, for a reach analysis, a second subset of user devices that belong to the first subset of user devices and the second set of user devices;
• identifying, for the reach analysis, a third subset of user devices that belong to the first subset or an intersection of the first data set and the second data set but not the second subset of user devices;
• computing, by the database server and for the reach analysis, a reach index within the first data set received from the first data source based at least in part on a ratio of a first number of user devices in the second subset to a second number of user devices in the third subset, wherein the computing comprises:
• determining, based at least in part on the ratio, a Jaccard index of the second subset of user devices and the third subset of user devices;
• and applying a binary entropy of information function to the determined Jaccard index;
• and
• transmitting, to a user device, an indication of the reach index within the first data set based at least in part on a result of the reach analysis, wherein the reach index indicates a quantity of user devices within the first set of user devices targeted to join the first subset of user devices in the first set of user devices.

An apparatus for data processing at a database server, comprising:

• a processor;
• memory in electronic communication with the processor;
• and instructions stored in the memory and executable by the processor to cause the apparatus to:
• receive, from a first data source, a first data set for a first set of user devices;
• identify, within the first set of user devices, a first subset of user devices characterized by a first set of attributes;
• receive, from a second data source different from the first data source, a second data set for a second set of user devices characterized by a second set of attributes;
• identify, for a reach analysis, a second subset of user devices that belong to the first subset of user devices and the second set of user devices;
• identify, for the reach analysis a third subset of user devices that belong to the first set of user devices and the second set of user devices;
• compute, by the database server and for the reach analysis, a reach index outside of the first data set received from the first data source based at least in part on a first ratio of a first number of user devices in the third subset to a second number of user devices in the first set of user devices or the second set of user devices but not the third subset of user devices and based at least in part on a second ratio of a third number of user devices in the second subset of user devices to the first number of user devices in the third subset, wherein the instructions executable by the processor to cause the apparatus to compute the reach index outside of the first data set are further executable to cause the apparatus to:
• determine, based at least in part on the first ratio, a Jaccard index of the first data set received from the first data source and the second data set received from the second data source;
• and
• apply a binary entropy of information function to the determined Jaccard index, wherein the second ratio is applied to the binary entropy of information function;
• and transmit, to a user device, an indication of the reach index outside of the first data set based at least in part on a result of the reach analysis, wherein the reach index indicates a quantity of user devices outside of the first set of user devices targeted to join the first subset of user devices in the first set of user devices.