Application of Machine Learning Algorithms in the Analysis of Social Vulnerability and Food Insecurity

• Pedro L. S. Lobo UFG
• Rogerio Salvini UFG
• Juliana Paula Felix UFG

DOI: https://doi.org/10.5753/erigo.2024.4792

Abstract

Hunger is a political and economic problem with profound social repercussions, with social vulnerability being an essential indicator for this understanding. This study applies machine learning methods to analyze food insecurity within the context of social vulnerability. Socioeconomic data from Fundação SEADE, RAIS, and CAISAN were used to create classification models that achieved F-score between 80% and 87% in categorizing the Paulista Index of Social Vulnerability (IPVS). Household income emerged as the most relevant factor. The results corroborate previous studies, indicating that socioeconomic data can be explored to identify indicators of vulnerability and food insecurity.

Keywords: machine learning, social vulnerability, food insecurity, socioeconomic data, household income

References

Bro, R., Kjeldahl, K., Smilde, A. K., and Kiers, H. A. (2008). Cross-validation of component models: A critical look at current methods. Analytical and Bioanalytical Chemistry, 390(5):1241–1251.

Fan, Y., Xuan, L., Qifeng, Z., and Linkai, L. (2011). Margin based variable importance for random forest. In 2011 6th International Conference on Computer Science Education (ICCSE), pages 1361–1366.

Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996). From data mining to knowledge discovery in databases. AI Magazine, 17(3):37.

Furness, B. W., Simon, P. A., Wold, C. M., and Asarian-Anderson, J. (2004). Prevalence and predictors of food insecurity among low-income households in los angeles county. Public Health Nutrition, 7(6):791–794.

Imron, M. A. and Prasetyo, B. (2020). Improving algorithm accuracy k-nearest neighbor using z-score normalization and particle swarm optimization to predict customer churn. Journal of Soft Computing Exploration, 1(1):56–62. Accessed: 30 Aug 2024.

Kolisetty, V. and Rajput, D. (2019). A review on the significance of machine learning for data analysis in big data. Jordanian Journal of Computers and Information Technology, 06:1.

Pérez-Escamilla, R. and Segall-Corrêa, A. M. (2008). Food insecurity measurement and indicators. Revista de Nutrição, 21:15s–26s.

Riyanto, S., Sitanggang, I., Djatna, T., and Atikah, T. (2023). Comparative analysis using various performance metrics in imbalanced data for multi-class text classification. International Journal of Advanced Computer Science and Applications, 14.

Sharif, Z. and Ang, M. (2001). Assessment of food insecurity among low income households in kuala lumpur using the radimer/cornell food insecurity instrument - a validation study. Malaysian journal of nutrition, 7:15–32.

Silva, M., Raposo, I., Silva, L., Assunção, J., Rolim, T., Souza, A., and Franco, F. (2020). VULNERABILIDADE SOCIAL, FOME E POBREZA NAS REGIÕES NORTE E NORDESTE DO BRASIL, pages 1083–1105.

Singh, A., Thakur, N., and Sharma, A. (2016). A review of supervised machine learning algorithms. In 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), pages 1310–1315.

Wong, T.-T. (2015). Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48(9):2839–2846.

Yuanyuan, S., Yongming, W., Lili, G., Zhongsong, M., and Shan, J. (2017). The comparison of optimizing svm by ga and grid search. In 2017 13th IEEE International Conference on Electronic Measurement Instruments (ICEMI), pages 354–360.