Understanding Over-Indebtedness in Portugal: Descriptive and Predictive Models

Research output: Book/ReportBook

Abstract

Over-indebtedness is a recurring problem in Portugal. After facing different economic cycles, between financial crises and prosperity periods, Portuguese consumers have been striving to keep their household finances stable and avoid being over-indebted. This project aims to gain insights on over-indebtedness, from different perspectives that range from the social to the economic point of view. It examines over-indebtedness from a psychological and from a data science perspective. In particular, we suggest that the systemic impact of financial crisis in Portugal not only promotes over-indebtedness, but it crafts a specific profile of over-indebted consumers which may be distinguished from other profiles, ranging from the emphasis on lack of self-regulation and careless management of one’s budget to other causal factors such as consumerism, crisis, and unemployment. Given this scenario, this project proposes the use of Machine Learning (ML) for developing descriptive and predictive models, to understand the influencing factors of over-indebtedness on Portuguese consumers and will be used for establishing consumer clusters and guidelines for over-indebtedness regulation and consumer financial empowerment.
Original languageEnglish
Place of PublicationLisboa
PublisherInstituto Superior de Estatística e Gestão de Informação da Universidade Nova de Lisboa. NOVA Information Management School (NOVA IMS)
Number of pages45
ISBN (Electronic)978-972-8093-20-4
Publication statusPublished - 22 Mar 2021

Keywords

  • Over-indebtedness
  • Portugal
  • Descriptive models
  • Predictive models
  • Self-Organizing Maps
  • Support Vector Machines

UN Sustainable Development Goals (SDGs)

  • SDG 1 - No Poverty
  • SDG 10 - Reduced Inequalities

Fingerprint Dive into the research topics of 'Understanding Over-Indebtedness in Portugal: Descriptive and Predictive Models'. Together they form a unique fingerprint.

Cite this