Spending Level of Displaced Population Returned to La Palma, Cundinamarca (2018): A Machine Learning Application

Abstract

This research aims to know the variables allowing to predict the spending level of the displacement victims that returned to La Palma, Cundinamarca. For this purpose, a measurement instrument was divided into four sections: characterisation of the population, restitution of economic rights, patterns of economic distribution and, finally, social innovation initiatives. We applied the instrument to 100 participants, and we use different Machine Learning algorithms to know the variables that allow predicting the level of expenses of the displacement victims that returned to La Palma, Cundinamarca. The findings permitted to observe that, at the aggregate level, the Random Forest and the SMV have a prediction capacity higher than 84%.