Anisha, S.S, Nargunam, S. and Shameem, Mohammed (2024) Machine learning methods to predict and classify poverty. In: Smart Technologies for Sustainable Development Goals: No Poverty. CRC Press, Boca Raton, pp. 159-177. ISBN 9781003519010

Full text not available from this repository.

Abstract

One of the main objectives of the global endeavour to achieve sustainable development is the eradication of poverty. Poverty is still a major problem, with many people across the world continuing to live in poverty and suffering despite tremendous advancements over the years. Estimating and classifying poverty levels is crucial for developing sustainable development plans and efficient policies. Robust methods for deciphering complex socioeconomic data and identifying the underlying trends and factors that contribute to poverty are provided by machine learning techniques. This chapter examines several machine learning techniques used to forecast and classify poverty levels, with a focus on achieving Sustainable Development Goal 1: the worldwide eradication of poverty in all of its forms. The current developments in model selection, data pre-processing, and feature selection that are specialized for problems related to poverty prediction are also reviewed. We are also discussing the challenges of interpretability, scalability, and data quality that arise when using machine learning models for the categorization of poverty. Our objective is to construct a system that uses machine learning approaches to assist in the creation of a precise and scalable system that predicts and classifies poverty.

Item Type:	Book Section
Identifier:	10.1201/9781003519010
Subjects:	Computing > Intelligent systems
Related URLs:	Publisher
Depositing User:	Marc Forster
Date Deposited:	07 Jan 2025 09:28
Last Modified:	07 Jan 2025 09:28
URI:	https://repository.uwl.ac.uk/id/eprint/13064

Actions (login required)

View Item