Estado del arte: algoritmos de Inteligencia Artificial para la medición de indicadores de pobreza.

Vitervo López Caballero

doi:10.46377/dilemas.v13i2.4866

Vitervo López Caballero Centro Nacional de Investigación y Desarrollo Tecnológico (CENIDET) https://orcid.org/0000-0002-1942-9558

DOI: https://doi.org/10.46377/dilemas.v13i2.4866

Palabras clave: medición de pobreza, algoritmo para la medición de pobreza, aprendizaje automático

Resumen

El propósito de este trabajo es presentar una revisión del estado del arte sobre los algoritmos más empleados en la medición de la pobreza a nivel global, con el fin de identificar enfoques analíticos vigentes y ofrecer estrategias que contribuyan a abordar este problema complejo y dinámico. La revisión realizada evidencia que los algoritmos con mayor presencia en la literatura reciente son las Redes Neuronales Convolucionales (CNN), Random Forest (RF), Gradient Boosting (incluido XGBoost) y las Redes Neuronales no Convolucionales. Las Redes Neuronales Convolucionales sobresalen por su alta efectividad en el procesamiento y extracción de características visuales, mientras que Random Forest y Gradient Boosting destacan por su versatilidad, capacidad predictiva y robustez en contextos diversos.

Citas

Ayush, K., Uzkent, B., Burke, M., Lobell, D., & Ermon, S. (2021). Generating interpretable poverty maps using object detection in satellite images. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 15072- 15081).

Banco Mundial (2020). Poverty and Shared Prosperity 2020: Reversals of Fortune. World Bank Publications.

Blumenstock, J., Cadamuro, G., & On, R. (2021). Predicting poverty and wealth from mobile phone metadata. Science, 371(6535), 1073-1077.

CIEB (2022). Clasificación de la pobreza en Bolivia, utilizando Random Forest y XGBoost. Cuadernos de Investigación Económica Boliviana, 5(1), 1-25.

Farooq, H. U., Nazar, M. J., Faisal, A., & Hanif, M. S. (2024). Using Satellite Imagery To Map Poverty Struck Areas of Pakistan Using Neural Networks.

Fatehkia, M., Tingzon, I., Orden, A., Sy, S., Sekara, V., Garcia-Herranz, M., & Weber, I. (2020). Mapping socioeconomic indicators using social media advertising data. EPJ Data Science, 9(1), 1-15.

Gram-Hansen, B., Helber, P., Varatharajan, I., Azam, F., Coca-Castro, A., Kopackova, V., & Bilbao, P. (2022). Mapping informal settlements in developing countries using machine learning and low resolution multi-spectral data. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 11, pp. 12307-12315).

Hallegatte, S., Rozenberg, J., & Vogt-Schilb, A. (2018). Climate change and socioeconomic impacts. In The Oxford Handbook of the Economics of Central Banking. Oxford University Press.

Head, A., Manguin, M., Tran, N., & Blumenstock, J. E. (2021). Can Human Development Be Measured with Satellite Imagery? In Proceedings of the Ninth International Conference on Learning Representations.

Jean, N., Morales, J., Gao, J., Lee, K., & Burke, M. (2023). Bridging the gap: Using deep learning to estimate poverty across countries. Nature Communications, 14(1), 1-10.

Knippenberg, E., Jensen, N., & Constas, M. (2021). Quantifying household resilience with high frequency data: Temporal dynamics and methodological options. World Development, 140, 105369.

Li, X., Zhou, Y., Chen, W., & Cai, Y. (2022). Mapping urban poverty using multi-source geospatial big data: A random forest approach. International Journal of Applied Earth Observation and Geoinformation, 114, 103027.

Liu, M., Hu, S., Ge, Y., Heuvelink, G. B., Ren, Z., & Huang, X. (2020). Using multiple linear regression and random forests to identify spatial poverty determinants in rural China. Spatial Statistics, 42, 100461.

Mahabir, R., Agouris, P., Stefanidis, A., Croitoru, A., & Crooks, A. T. (2023). Detecting and mapping slums using open data: a case study in Kenya. International Journal of Digital Earth, 16(1), 1-27.

Mariati, N. P. A. M., Budiantara, I. N., & Ratnasari, V. (2019, December). Modeling poverty percentages in the Papua Islands using Fourier series in nonparametric regression multivariable. In Journal of Physics: Conference Series (Vol. 1397, No. 1, p. 012071). IOP Publishing.

Merfeld, J. D., & Morduch, J. (2023). Poverty at higher frequency. KDI School of Public Policy & Management Paper No. DP23-03.

Naciones Unidas (2023). Sustainable Development Goals Report 2023. United Nations Publications.

Niu, T., Chen, Y., & Yuan, Y. (2020). Measuring urban poverty using multi-source data and a random forest algorithm: A case study in Guangzhou. Sustainable Cities and Society, 54, 102014.

Njuguna, C., & McSharry, P. (2020). Constructing spatiotemporal poverty indices from big data. Journal of Business Research, 131, 606-615.

Okiabera, J. O. (2020). Using random forest (RF) to identify key determinants of poverty in Kenya (Doctoral dissertation, University of Nairobi).

Piaggesi, S., Gauvin, L., Tizzoni, M., Cattuto, C., Adler, N., Verhulst, S., ... & Panisson, A. (2019). Predicting city poverty using satellite imagery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 90-96).

Ratledge, N., Cadamuro, G., De la Fuente, A., Castillo, M. G., & Foster, V. (2022). Using satellite imagery and machine learning to estimate the livelihood impact of electricity access. Nature Communications, 13(1), 1-12.

Ravallion, M. (2020). On measuring global poverty. Annual Review of Economics, 12(1), 167-188.

Sohnesen, T. P., Ambel, A. A., Fisker, P., Malmgren-Hansen, D., & Asher, S. (2023). Estimating poverty in data-scarce environments: A new approach combining satellite images and machine learning. World Development, 161, 106076.

Steele, J. E., Sundsøy, P. R., Pezzulo, C., Alegana, V. A., Bird, T. J., Blumenstock, J., ... & Bengtsson, L. (2020). Mapping poverty using mobile phone and satellite data. Journal of The Royal Society Interface, 14(127), 20160690.

Tingzon, I., Orden, A., Go, K., Sy, S., Sekara, V., Weber, I., ... & Fatehkia, M. (2021). Mapping poverty in the Philippines using machine learning, satellite imagery, and crowd-sourced geospatial information. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 15, pp. 892- 903).

Wu, P., & Tan, Y. (2019). Estimation of poverty based on remote sensing image and convolutional neural network.

Wu, P., & Tan, Y. (2019, November). Estimation of economic indicators using residual neural network ResNet50. In 2019 International conference on data mining workshops (ICDMW) (pp. 206-209). IEEE.

Xie, M., Jean, N., Burke, M., Lobell, D., & Ermon, S. (2021). Transfer learning from deep features for remote sensing and poverty mapping. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 30, No. 1).

Yeh, C., Perez, A., Driscoll, A., Azzari, G., Tang, Z., Lobell, D., ... & Burke, M. (2022). Using publicly available satellite imagery and deep learning to understand economic well-being in Africa. Nature Communications, 11(1), 1-11.

Zhao, X., Yu, B., Liu, Y., Chen, Z., Li, Q., Wang, C., & Wu, J. (2019). Estimation of poverty using random forest regression with multi-source data: A case study in Bangladesh. Remote Sensing, 11(4), 375.

Zhao, X., Yu, B., Liu, Y., Chen, Z., Li, Q., Wang, C., & Wu, J. (2022). Estimation of poverty in rural areas of the conterminous United States using Landsat imagery and machine learning methods. Remote Sensing of Environment, 252, 112159.