Understanding cities: A data science perspective
The transition of data from being a scarce resource to a massive and real-time processed stream is rapidly changing the world we live in, challenging and often subverting long-lasting paradigms in a broad range of domains. Finance, economics, politics, journalism, medicine, biology, and physics, to name a few, have been disrupted by the existence of large amounts of data. The almost universal adoption of mobile phones, the exponential growth in the usage of Internet services and social media platforms, and the proliferation of digital payment systems, wearable devices, and connected objects has led to the existence of unprecedented amounts of data about human behavior. We live in an unprecedented historic moment where the availability of vast amounts of human behavioral data, combined with advances in machine learning, are enabling us to build predictive computational models of human behavior.
In my talk, I will show examples of how those computational models of human behaviors can be used to better understand cities, For example, I will present some recent works where I have leveraged data from public (e.g. national census) and from commercial entities (e.g. Foursquare Point of Interests, mobile phone data, credit card transactions, Google Street View images) in order (i) to infer how vital and liveable a city is, (ii) to find the urban conditions (e.g. mixed land use, people’s daily routines and mobility patterns, people’s safety perceptions, etc.) that magnify and influence urban life, and (iii) to study their relationship with societal outcomes such as poverty, criminality, innovation, segregation.