Community detection algorithm for complex networks

Community detection is key to understanding the structure of complex networks, and ultimately extracting useful information from them. Applications are diverse: from healthcare to regional geography, from human interactions and mobility to economics. We present a novel search strategy for the optimization of various objective functions for community detection purposes.

Borderline: visualization of community detection in UK phone communication network delineating geographical regions, MIT-British Telecom collaboration

Over the past decade, the development of digital networks and operations has produced an unprecedented wealth of information. Handheld electronics, location devices, telecommunications networks, and a wide assortment of tags and sensors are constantly producing a rich stream of data reflecting various aspects of urban life. The 'Network & Society' project at the MIT Senseable City Lab employs these large-scale digital datasets to explore physical mobility, social networks and urban places. One of the applications is regional delineation.

Spring spree: Discovering patterns of human spending behavior through anonyzmized dataset of credit card transactions in Spain, MIT-BBVA collaboration

The Senseable City Lab together with leading Spanish bank BBVA has embarked on an examination of expenditure patterns and urban analysis at large, using an unprecedented dataset of financial transactions. The first in a series of studies, Spring Spree illustrates the purchasing patterns across Spain during Easter 2011. Further project development led to research publications in leading big data conferences and improvement of existing bank's credit scoring system for small businesses. Project ongoing with particular focuses on credit risk and location microeconomic scoring.

Singature of Humanity: Understanding human behavior in cities through cell phone data, MIT-Ericsson collaboration

As digital technologies are becoming more and more widespread, data from communication networks allow us to better understand human behavior. The exploration of these data provides many new perspectives, revealing characteristic usages and regular dynamic patterns at both the individual and collective scale. The Senseable City Lab and Ericsson have embarked on a journey inside an unprecedented communications network data set including networks from different parts of the world. Our leading project aims at exploring the spatio-temporal voice, sms and data traffic in major cities from various continents.