Columbia University computer science professor Tony Jebara has developed Citysense, a tracking software service that can highlight the hottest clubs and hangouts in real time, similar to how a Doppler system highlights inclement weather.
Citysense uses advanced machine learning techniques to process vast amount of data gathered from thousands of cell phones, GPS-equipped cabs and other data devices to paint live pictures of where people are gathering. Citysense calculates how many people are at each location and enables users to look on their cell phones to see which places are drawing the biggest crowds. The technology can also be used to see if traffic is backed up or flowing.
All information gathered is anonymous, the data could be used by marketers and consumer researchers looking to enhance sales pitches, learn where people actually shop, or don’t, and tweak emerging retail trends as they evolve.
Jebara says that “there is no single equation describing human activity, but by computing statistics from millions of locations and flow between them, it becomes possible to find clusters, trends, explanations and predictive patterns.”
This is a very interesting technology, especially in the field of machine learning. More on machine learning can be found at http://www.aaai.org/AITopics/pmwiki/pmwiki.php/AITopics/MachineLearning
David Poratta (2008) Available at: http://www.columbia.edu/cu/news/08/06/citysense.html