UTILIZING LOGISTIC REGRESSION TO IDENTIFY HOUSEHOLD POVERTY STATUS IN BENUE STATE OF NIGERIA
Abstract
Despite numerous poverty alleviation programmes in Nigeria, household poverty continues to rise. This paper aimed to improve poverty detection by analyzing household socio-economic and environmental data using logistic regression models. Data was collected through Google forms and pre-processing and feature extractions were performed. Five logistic models were developed to represent different types of poverty. The models were evaluated for accuracy, precision, recall, and F1 score, achieving 80% for Absolute Poverty and 100% for Chronic/Structural, Conjectural/Transitory, and Locational/Spatial poverty. The analysis revealed that over half of the households were poor, with Spatial/Locational poverty being the most prevalent. Targeting this type of poverty is recommended for effective intervention.
References
Adamu, B. D., Tanko, F., Barnabas, T. M. a. & Adejoh, E. U. (2021). Determinants of Household’s Poverty Among Crop Farmers In Kaduna State, Nigeria. FUDMA Journal of Sciences (FJS), 5(1):529-530.
Abdirizak A. H., Abdisalam H. M. & Christophe C. (2024). Machine learning study using 2020 SDHS data to determine poverty determinants in Somalia. https://www.nature.com/articles/s41598-024-56466-8
Adham, A., Mohammad, A., Maha, D., Heba, S. & Musa, A. (2021). Poverty Classification Using Machine Learning: The Case of Jordan. Multidisciplinary Digital Publishing Institute. https://www.researchgate.net/publication/348898452_Poverty_Classification_Using_Machine_Learning_The_Case_of_Jordan .
Alsharkawi, A., Al-Fetyani, M., Dawas, et al. (2021). Poverty Classification Using Machine Learning: The Case of Jordan Sustainability. https://www.mdpi.com/2071-1050/13/3/1412
Aziza Usmanova (2022). Utilities of Artificial Intelligence in Poverty Prediction: A Review. Sustainability. Econpapers. https://econpapers.repec.org/article/gamjsusta/v_3a14_3ay_3a2022_3ai_3a21_3ap_3a14238-_3ad_3a959346.htm
Blumenstock, J. E., Cadamuro, G., & On, R. (2015). Predicting poverty and wealth from mobile phone metadata. https://www.unhcr.org/innovation/wp-content/uploads/2016/11/blumenstock-science-2015.pdf
Chenhong P., Lue F., Julia S. W. & Paul S. F. Y. (2019). Determinants of Poverty and Their Variation Across the Poverty Spectrum: Evidence from Hong Kong, a High-Income Society with a High Poverty Level. Social Indicators Research, 144(1), 219–250.DOI: 10.1007/s11205-018-2038-5
Dedy R., Raden I., Fadhilah I., Elis H. & Wawa W. (2024). Poverty prediction using E-commerce dataset and filter-based feature selection approach. Scientific Report. https://www.nature.com/articles/s41598-024-52752-7
Doris D. S. (2022). Poverty headcount rate in Nigeria 2019, by state. https://www.statista.com/statistics/1121438/poverty-headcount-rate-in-nigeria-by-state/#statisticContainer
Emily, A., Suzanne, B., Dean, K., Chris, U. & Joshua, E. B. (2022). Machine Learning and Phone Data can Improve Targeting of Humanitarian Aid. https://www.nature.com/articles/s41586-022-04484-9.
GeeksforGeeks (2023). Logistic Regression in Machine Learning. Retrieved from https://www.geeksforgeeks.org/understanding-logistic-regression/ .
International Monetary Fund. (2017). Malawi Economic Development Document.
Ji , Y. K. (2021). Using Machine Learning to Predict Poverty Status in Costa Rican Households. Johns Hopkins University, Carey Business SchoolWashington, DC. https://www.semanticscholar.org/reader/fe12f04fdd4d38a94909ce8a008d7ddb06c3c0de.
Liu, M., Hu, S., Ge, Y., Heuvelink, G. B., Ren, Z., & Huang, X. (2021). Using multiple linear regression and random forests to identify spatial poverty determinants in rural China. Spatial Statistics, 42, 100461. https://research.wur.nl/en/publications/using-multiple-linear-regression-and-random-forests-to-identify-s.
Majeed, M. T., & Malik, M. N. (2015). Determinants of Household Poverty: Empirical evidence from Pakistan. The Pakistan Development Review, 54(4I-II), 701–718. https://www.jstor.org/stable/43831356#:~:text=determinants.,-6.&text=of%20household%20poverty%20in%20Pakistan,location%2C%20household%20size%20and%20remittances .
Morten, J. (2013). Poor numbers. In Poor Numbers. Cornell University Press.
National Bureau of Statistics. (2022). Nigeria Launches its Most Extensive National Measure of Multidimensional Poverty. Press Released in Abuja. https://nigerianstat.gov.ng/news/78#:~:text=Highlights%20of%20the%202022%20Multidimensional,quarter%20of%20all%20possible%20deprivations .
Pa, P. M., Yen, W. G., Siti, N. B. H., Thian, S. O., & Shohel, S. (2022). Poverty Prediction Using Machine Learning Approach. Journal of Southwest Jiaotong University. Faculty of Information Science and Technology, Multimedia University Melaka, Malaysia. http://jsju.org/index.php/journal/article/view/1162
Rekha G S, Shivanshu P, Samarth C., Shweta P. & Rohan S. (2023). Poverty Detection Using Deep Learning and Image Processing. IJraset Journal for Research in Applied Science and Engineering Technology. DOI Link: https://doi.org/10.22214/ijraset.2023.50518
Satej, S., Emily, A., Esther, R. & Joshua, B. (2022). Can Strategic Data Collection Improve the Performance of Poverty Prediction Models? 36th Conference on Neural . Information Processing Systems (NeurIPS 2022). https://www.researchgate.net/publication/365448864_Can_Strategic_Data_Collection_Improve_the_Performance_of_Poverty_Prediction_Models .
Sonia, J. (2022). How Does Logistic Regression Work. https://www.kdnuggets.com/author/sonia-jessica.
United Nations Development Programme. (2019). Multi-Dimensional Poverty ReportReveals Wide Inequalities Among the Poor United Nations. The Sustainable Development Goal Report 2019. New York: United Nations. https://sdg.iisd.org/news/undp-multi-dimensional-poverty-report-reveals-wide-inequalities-among-the-poor/.
Vatcheva, K. P., Lee, M., McCormick, J. B., & Rahbar, M. H. (2016). Multicollinearity in Regression Analyses Conducted in Epidemiologic Studies. Epidemiology (Sunnyvale, Calif.), 6(2), 227.
Wang S. and Shi, Y. (2021). Prediction Poverty Levels of College Students Using a Machine Learning Model. Chuzhou University. Posted Date: https://doi.org/10.21203/rs.3.rs-919541/v1 .
World Bank (2020). DataBank. https://databank.worldbank.org/source/poverty-and-equity-database. https://econpapers.repec.org/article/gamjsusta/v_3a14_3ay_3a2022_3ai_3a21_3ap_3a14238-_3ad_3a959346.htm
World Bank (2022).Understanding Poverty 2022 https://www.worldbank.org/en/topic/poverty/overview
Copyright (c) 2024 FUDMA JOURNAL OF SCIENCES
This work is licensed under a Creative Commons Attribution 4.0 International License.
FUDMA Journal of Sciences
