Improved Poverty Tracking and Targeting in Jordan Using Feature Selection and Machine Learning

Abstract

This paper improves on a recently proposed machine learning approach to assess and monitor the poverty status of Jordanian households. Without a doubt, accurate identification, tracking, and targeting households in poverty is a key to poverty alleviation. This work presents a nontraditional approach to the accurate prediction of poverty for Jordanian households using feature selection and machine learning. This approach can be seen as a support in the decision making process in the government and non-governmental organizations in an ever-shifting socio-economic environment. Using the Jordanian household expenditure and income surveys collected by the Department of Statistics (DoS), LightGBM predictive performance is improved to reach 83% F1-Score using only 41 features in contrast to 81% F1-score and 96 features in our previous work. At the heart of this work is determining which variables of household expenditure and income surveys are most predictive and how they can be most effectively combined. National surveys can now be run with fewer, more targeted questions that can greatly help in assessing the effectiveness of new policies and intervention programs rapidly and cheaply.