Show simple item record

dc.contributorArias Vicente, Marta
dc.contributor.authorCalvo Fantova, Santiago
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.date.accessioned2020-07-01T08:31:44Z
dc.date.available2020-07-01T08:31:44Z
dc.date.issued2020-01-27
dc.identifier.urihttp://hdl.handle.net/2117/192080
dc.description.abstractMany socio-economic studies are nowadays trying to accomplish a complete description of how the different elements of our society and world are connected. This work is an attempt to build an architecture that provides an explanation of the connections and impacts that exist among the different indicators (for now on also mentioned as sectors) of a state or population (Agriculture, Climate Change, Economy & Growth, Energy & Mining, Education, Health, Poverty, Science & Technology, Social Development, and others). We will focus our effort in the research of, not only the correlations that may exist between these indicators and thought the different countries analyzed, but also the causality that relates them. With causality (we will deploy a Bayesian Network architecture for each country to accomplish this task), we will be able to describe the impact and influence that one indicator may have in the others. This could lead to an accurate, powerful and global knowledge of the functioning of our world and each single country in particular, along with a vision of the dependencies between the different indicators that describe a country. Finally, we will also propose a clustering model where each individual will be a representation of the Bayesian Network obtained for each country. With this model, we will provide N aggrupation of countries with their Bayesian Network representation for each one, which will give us a global vision of the functioning of our world represented by the causal relationships between the different indicators that can be found in our countries or populations
dc.language.isoeng
dc.publisherUniversitat Politécnica de Catalunya
dc.publisherUniversitat Politècnica de Catalunya
dc.subjectÀrees temàtiques de la UPC::Informàtica
dc.subject.lcshNeural networks (Computer science)
dc.subject.otherData Analysis
dc.subject.otherPCA
dc.subject.otherAutoencoder
dc.subject.otherNeural Networks
dc.subject.otherBayesian Networks
dc.subject.otherCausality
dc.subject.otherCountry Indicators
dc.subject.otherSocio-Economic factors
dc.subject.otherCorrelation
dc.subject.otherDirected Acyclic Graph
dc.subject.otherClustering.
dc.subject.otherData Analysis
dc.subject.otherPCA
dc.subject.otherAutoencoder
dc.subject.otherNeural Networks
dc.subject.otherBayesian Networks
dc.subject.otherCausality
dc.subject.otherCountry Indicators
dc.subject.otherSocio-Economic factors
dc.subject.otherCorrelation
dc.subject.otherDirected Acyclic Graph
dc.subject.otherClustering.
dc.titleData analysis of socio-economic and financial factors from a public world-wide source
dc.typeMaster thesis
dc.subject.lemacXarxes neuronals (Informàtica)
dc.subject.lemacAnàlisi de dades
dc.identifier.slug147843
dc.rights.accessOpen Access
dc.date.updated2020-06-09T04:00:48Z
dc.audience.educationlevelMàster
dc.audience.mediatorFacultat d'Informàtica de Barcelona
dc.audience.degreeMÀSTER UNIVERSITARI EN INNOVACIÓ I RECERCA EN INFORMÀTICA (Pla 2012)


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder