Luka Urban\u010d, Marko Grobelnik and Joao Pita Costa<\/p>\n
Abstract<\/strong> \u00a0<\/p>\n\n\n\n\n\n
Although Poverty reduction being set as the first sustainable de-
velopment goal set to be reached in 2030 by the United Nations,
data indicates that progress might be far from expected by the
end date. Moreover, the parameters affecting poverty levels at
the different nations is diverse and makes it extremely difficult to
establish a reasonable machine learning approach to contribute
to that aim. This paper uses a variety of regression models to
predict poverty rates. The models are built using a wide selection
of data, which is preprocessed and used to generate different
files before being used to train an OLS linear regression model, a
lasso regression model, a ridge regression model and an elastic
net regression model. We were successful in creating a ridge re-
gression model with a RMSE of 3.6%, which would be considered
high, especially after taking into account the fact that the model
works on a global basis and is not limited to a specific area or
group of countries.<\/p>\n