Providing wireless services based on using subscriber geospatial activity

A system, comprising:

• one or more processors;
• one or more memories that are coupled to the one or more processors and storing program instructions for classifying subscribers of a wireless network, wherein the program instructions, when executed by the one or more processors, cause the system to perform operations comprising:
• creating an augmented graph for each subscriber of a plurality of subscribers of the wireless network based on their respective geospatial activity;
• extracting, using a first machine learning model, a plurality of features from the respective augmented graph of each subscriber of the plurality of subscribers;
• creating an embedding for the respective plurality of features of each subscriber of the plurality of subscribers;
• and
• classifying, using a second machine learning model, the plurality of subscribers into a plurality of groups of subscribers based on the respective embedding of each subscriber of the plurality of subscribers.

A non-transitory computer readable storage medium storing program instructions for classifying subscribers of a wireless network, wherein the program instructions, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• creating an augmented graph for each subscriber of a plurality of subscribers of the wireless network based on their respective geospatial activity;
• extracting, using a first machine learning model, a plurality of features from the respective augmented graph of each subscriber of the plurality of subscribers;
• creating an embedding for the respective plurality of features of each subscriber of the plurality of subscribers;
• and
• classifying, using a second machine learning model, the plurality of subscribers into a plurality of groups of subscribers based on the respective embedding of each subscriber of the plurality of subscribers.