{"id":9750,"date":"2023-07-10T17:28:26","date_gmt":"2023-07-10T20:28:26","guid":{"rendered":"http:\/\/fund.ar\/publicacion\/from-ushuaia-to-la-quiaca-byte-by-byte-how-to-boost-the-tourism-industry-with-big-data\/"},"modified":"2024-05-22T14:47:34","modified_gmt":"2024-05-22T17:47:34","slug":"from-ushuaia-to-la-quiaca-byte-by-byte-how-to-boost-the-tourism-industry-with-big-data","status":"publish","type":"publicacion","link":"https:\/\/fund.ar\/en\/publicacion\/from-ushuaia-to-la-quiaca-byte-by-byte-how-to-boost-the-tourism-industry-with-big-data\/","title":{"rendered":"From Ushuaia to La Quiaca: byte by byte. How to boost the tourism industry with big data"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Big data goes a long way to gain knowledge about the population. Its volume and granularity enable conclusions often overlooked in traditional sources (polls, interviews or official records). Although commonly used for customer segmentation, its potential for understanding the population targeted by public policies remains untapped. This paper explores, specifically from the perspective of the Federal Ministry of Tourism and Sports, the potential of these alternative data sources for improving the design and implementation of public policies.<\/strong><\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Illustration: Noe Garin<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Big data for public policy-making<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The State requires information for decision-making, effective public policy design and impact assessment. It needs data on the population targeted by these policies and the context in which they are to be implemented. In this sense, the information available at state level is usually imperfect and inadequate. However, the use of alternative sources of information is not a common practice for the public administration.<\/span><\/p>

Can big data coexist with traditional sources and add to the information readily available to find those the state engages or speaks with? This paper presents a joint experience between Fundar, the National Directorate of Markets and Statistics of the Federal Ministry of Tourism and Sports and the Laboratory of Discrete Event Simulation of the School of Exact and Natural Sciences, University of Buenos Aires. It seeks to improve analysis and understanding of domestic tourism flows and to provide new information on tourism markets for the implementation of public policies in the sector.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Traditional sources \/ alternative sources<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The Federal Ministry of Tourism and Sports has several information-gathering tools. These include the Federal Tourism Data Management System of Argentina, the Household Travel and Tourism Survey (EVyTH) and the Hotel Occupancy Survey (EOH). However, these sources do not provide all the information needed. For this reason, we considered supplementing them with another source, in particular one that would provide geographic and temporal disaggregation.<\/span><\/p>

The secondary source used is a georeferenced database that collects data from mobile devices. It offers information on the point of origin of trips made throughout the national territory, with daily temporal granularity and a breakdown by destination. In this way, it provides those involved in the tourism industry with more detailed information on the origin and destination of trips, thus enabling an analysis of the routes taken to get from one point to another.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Big data methodology<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The starting point of the process is a database containing anonymous information from mobile devices that are identified using a unique advertising code or IFA (Identifier for Advertising). Each of these IFAs is assumed to be an individual. Since the information is anonymous, this data provides an overview of the characteristics of the local population, without the possibility of associating this record to any particular individual.<\/span><\/p>

The database contains daily georeferenced records, from April 2019 to March 2020, from the 528 departments, districts and communes of the 23 provinces and the Federal Capital of Argentina (except Antarctica and South Atlantic islands).<\/span><\/p>

Each IFA (or unique user) was assigned a place of residence, which was identified based on the most common georeferenced evening location (CEL). This geographic coordinate also allows each IFA to be linked to a set of socioeconomic characteristics associated with that residential area. Their trips were also analyzed, assuming a trip is for tourism if the IFA is found at a certain minimum distance from the place of residence (40\u00a0km for the Metropolitan Area of Buenos Aires and 20 km for the rest of the country).<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Monthly trip comparison<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

A first exercise was to compare the data obtained from primary and secondary sources on the trips made each month. As in the EVyTH design, this was done by filtering the data provided by the secondary source for trips with the same origin (i.e. from one of the large urban agglomerations) and destination within specific requirements in terms of distance traveled and traveler\u00b4s usual environment during the same reference period (April 2019 – March 2020). <\/span><\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t