Location data is everywhere. Cars, buses, taxis, mobile phones, cameras, and personal navigation devices all beacon their locations thanks to network-connected positioning technologies such as GPS, WiFi and cell tower triangulation. Millions of consumers and businesses use location-enabled devices for finding nearby services, locating friends & family, navigating, asset- and pet-tracking, dispatching, sports, games, and hobbies.




Recently, two market forces have caused an explosion in the number of Internet connected location-enabled devices:

• A government safety initiative, E-911, mandated that
  mobile phones must be locatable in case of an
  emergency call
  


• Massive demand for navigation services and real-time
  traffic information

These forces have lowered the cost of technology, ignited interest in location-enabled services, and resulted in the generation of significant amounts of historical and real-time streaming location information. Sense Networks was founded on the idea that these datasets could provide remarkable real-time insight into aggregate human activity trends.

Macrosense employs patent-pending technology to learn from these large-scale patterns of movement, and to identify distinct classes of behaviors in specific contexts, called "tribes."

Each color dot in the above visualization represents the presence of a particular nightlife tribe at a particular place and time – a type of people group who move around the city in a similar way, and visit similar places at similar times. This simplified animation shows the changing whereabouts of these tribes over the course of an evening.

Once it's known which tribes are where, by sampling the distribution of tribes at any given place and time, it's possible to understand what it means when a user is there at that place and time.

For example: rock clubs and hip-hop clubs each retain distinct tribal distributions. When a user is out at night, Citysense learns their preferred tribe distribution from time spent in these places. When that user visits another city, they see hotspots recommended on the basis of this distribution and combined with overall activity information.

Users who go to rock clubs see rock club hotspots, users who frequent hip-hop clubs see hip-hop hotspots, and those who go to both see both. The question "where is everybody like me right now?" is thus answered for these users – even in a city they've never visited before.

Simulating the real world via the use of tribes makes it possible to provide personalized services to each user without collecting personally identifiable information.