AGRANDA 2015, 1º Simposio Argentino de Grandes Datos. The City Pulse of Buenos Aires Carlos Sarraute 1 , Carolina Lang 1 , Nicolas B. Ponieman 1 , and Sebastian Anapolsky 2 1 Grandata Labs, Argentina 2 Mobility and transport specialist 1 Introduction Cell phone technology generates massive amounts of data. Although this data has been gathered for billing and logging purposes, today it has a much higher value, because its volume makes it very useful for big data analyses. In this project, we analyse the viability of using cell phone records to lower the cost of urban and transportation planning, in particular, to find out how people travel in a specific city (in this case, Buenos Aires, in Argentina). We use cell phones data to estimate the distribution of the population in the city using different periods of time. We compare those results with traditional methods (urban polling) using data from Buenos Aires origin-destination surveys. Traditional polling methods have a much smaller sample, in the order of tens of thousands (or even less for smaller cities), to maintain reasonable costs. Furthermore, these studies are performed at most once per decade, in the best cases, in Argentina and many other countries. Our objective is to prove that new methods based on cell phone data are reliable, and can be used indirectly to keep a real-time track of the flow of people among different parts of a city. We also go further to explore new possibilities opened by these methods. 2 Mobile Data Source We applied our methodology to Buenos Aires city, the capital of Argentina, which has 2,890,151 inhabitants [1] and is the main political, financial and cultural center of the country. Buenos Aires city is formally divided in 48 neighborhoods, which are grouped for political and administrative purposes in 15 communes. We have a dataset of geolocalized CDR (call detail records), from which we examine the mobility patterns of mobile phone users. The high penetration of cell phone technol- ogy in the city allows us to estimate the mobility patterns of all the inhabitants from this data. Our dataset has about 4.95 million mobile phone users (1,000 times the number of people in the Buenos Aires survey [2]); it also contains more than 200 million call records generated by these users during a period of five months (from November 1st, 2011 to March 30th, 2012). Each record contains the origin (caller), destination (callee), timestamp, duration of the call and antenna used to connect. In addition, we have the geolocalization of the antennas. We used that information to map the antennas to a certain commune, and we used the map [call→antenna] as dataset of geolocated calls. 44JAIIO - AGRANDA 2015 - ISSN: 2451-7569 34