0521/2016 - Prediction of the Human Development Index and Life Expectancy in Latin American Countries using Data Mining Techniques
Previsão do Índice de Desenvolvimento Humano e da Expectativa de Vida nos Países da América Latina por meio de Técnicas de Mineração de Dados
Publicado
Author:
• Celso Bilynkievycz dos Santos - Santos, C.B - Ponta grossa - Universidade Tecnologica Federal do Parana - <bilynkievycz@uepg.br>ORCID: https://orcid.org/0000-0003-2107-8299
Co-author(s):
• Luiz Alberto Pilatti - Pilatti, L.A. - Universidade Tecnológica Federal do Paraná, Pós-Graduação - <lapilatti@utfpr.edu.br>• Bruno Pedroso - Pedroso, Bruno - Universidade Estadual de Ponta Grossa - <prof.brunopedroso@gmail.com>
• Deborah Riberio Carvalho - Carvalho, Deborah Riberio - Pontificia Universidade Catolica do Parana - <drdrcarvalho@gmail.com>
• Alaine Margarete Guimarães - Guimarães, Alaine Margarete - Universidade Estadual de Ponta Grossa - <alainemg@uepg.br>
Thematic Area:
Ciências SociaisAbstract:
The predictability of epidemiological indicators can help estimate dependent variables, assist in decision making to support public policies, and justify the scenarios experienced by different countries worldwide.Aim: This study aimed to predict the Human Development Index and life expectancy in Latin American countries in the period of 2015–2020 using data mining techniques.
Methods: All stages of the process of knowledge discovery in databases were covered. The SMOReg algorithm of data mining was used in the models with multivariate time series to make predictions; this algorithm performed the best in the tests developed during the evaluation period.
Results: The average Human Development Index and life expectancy in Latin American countries showed an increasing trend in the period evaluated and corresponded to 4.99±3.90% and 2.65±0.06 years, respectively.
Conclusion: Multivariate models allow for greater evaluation of algorithms, thus increasing their accuracy. Data mining techniques have better quality in predictions regarding the most popular technique, ARIMA In addition, the predictions suggest that there will be a higher increase in the mean HDI and LE in Latin American countries compared to the mean values in the rest of the world.
