The Forecasting of Poverty using the Ensemble Learning Classification Methods
DOI:
https://doi.org/10.31436/ijpcc.v9i1.326Keywords:
Machine Learning, Random Forest, Gradient Boosting, Extreme Gradient Boosting, XGBoost, Ensemble Learning Classification MethodsAbstract
Poverty is a social-cultural problem that can be categorized into monetary approach, capability approach, social exclusion, and participatory poverty assessment. However, the existing measurement methods are complex, costly, and time-consuming. This research was conducted to forecast poverty using classification methods. Random Forest and Extreme Gradient Boosting (XGBoost) algorithms were applied to forecast poverty since they are supervised learning algorithms that use the ensemble learning approach for classification. Ensemble Learning has improved the classification of poverty and obtained better predictive performance. The results of the algorithms showed the poverty trend, which helped to determine the poverty classification. Hence, this method will help the government to act and produce a specific plan to reduce the poverty rate. It is a strategic move to reduce global poverty, parallel to Goal 1 of Sustainable Development Goal (SDG): No Poverty
References
A. A. Bakar, R. Hamdan, and N. S. Sani, “Ensemble learning for multidimensional poverty classification,” Sains Malaysian, vol. 49, no. 2, pp. 447–459, 2020, doi: 10.17576/jsm-2020-4902-24.
United Nations, “A UN framework for the immediate response to Table of Contents,” United Nations, no. April, 2020.
U. Nations, “Shared Responsibility, Global Solidarity: Responding To the Socio-Economic Impacts of Covid-19,” United Nations, no. March, pp. 1–26, 2020, [Online]. Available: https://www.un.org/sites/un2.un.org/files/sg_report_socio-economic_impact_of_covid19.pdf.
A. Sumner, C. Hoy, and E. Ortiz-Juarez, “Estimates of the impact of COVID-19 on global poverty,” UNU WIDER Work. Pap., no. April, pp. 1–9, 2020, [Online]. Available: https://doi.org/10.35188/UNU-WIDER/2020/800-9.
N. S. Sani, M. A. Rahman, A. A. Bakar, S. Sahran, and H. M. Sarim, “Machine learning approach for Bottom 40 Percent Households (B40) poverty classification,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 8, no. 4–2, pp. 1698–1705, 2018, doi: 10.18517/ijaseit.8.4-2.6829.
J. H. Mohamud and O. N. Gerek, “Poverty level characterization via feature selection and machine learning,” 27th Signal Process. Commun. Appl. Conf. SIU 2019, pp. 6–9, 2019, doi: 10.1109/SIU.2019.8806548.
S. K. Venkatramolla, “Machine Learning and Data Science for a Household-Specific Poverty Level Prediction Task,” 2019.
P. Kambuya, “Better model selection for poverty targeting through machine learning: A case study in Thailand,” Thail. World Econ., vol. 38, no. 1, pp. 91–116, 2020.
Sarwosri, D. Sunaryono, R. J. Akbar, and R. D. Setiyawan, “Poverty classification using Analytic Hierarchy Process and k-means clustering,” Proc. 2016 Int. Conf. Inf. Commun. Technol. Syst. ICTS 2016, pp. 266–269, 2017, doi: 10.1109/ICTS.2016.7910310.
D. R. Wijaya, N. L. P. S. P. Paramita, A. Uluwiyah, M. Rheza, A. Zahara, and D. R. Puspita, “Estimating city-level poverty rate based on e-commerce data with machine learning,” Electron. Commer. Res., no. 0123456789, 2020, doi: 10.1007/s10660-020-09424-1.
J. A. Talingdan, “Performance comparison of different classification algorithms for household poverty classification,” Proc. - 2019 4th Int. Conf. Inf. Syst. Eng. ICISE 2019, pp. 11–15, 2019, doi: 10.1109/ICISE.2019.00010.
H. Zixi, “Poverty Prediction through Machine Learning,” Proc. - 2nd Int. Conf. E-Commerce Internet Technol. ECIT 2021, pp. 314–324, 2021, doi: 10.1109/ECIT52743.2021.00073.
G. Cicceri, G. Inserra, and M. Limosani, “A machine learning approach to forecast economic recessions-an Italian case study,” Mathematics, vol. 8, no. 2, pp. 1–20, 2020, doi: 10.3390/math8020241.
P. Gogas and T. Papadimitriou, “Machine Learning in Economics and Finance,” Comput. Econ., vol. 57, no. 1, pp. 1–4, 2021, doi: 10.1007/s10614-021-10094-w.
