Predicting Urban Performance through Behavioral Patterns in Temporal Telecom Data
This study explores a novel method to analyze diverse behavioral patterns in large urban populations and to associate them with discrete urban features. This work utilizes machine learning and anonymized telecom data to understand which fragments of the city has greater potential to attract dense and diverse populations over longer periods of time. Finally, this work suggests a road map for building spatial prediction tools in an effort to improve city-design and planning processes.
Advisors: Kent Larson and Esteban Moro
Thanks to Andorra Telecom, ActuaTech, Núria Macià.
Data was obtained by Andorra Telecom as part of MIT Media Lab City Science and the State of Andorra collaboration.