Modelo predictivo para identificar hogares beneficiarios de programas de transferencias monetarias: una comparación de técnicas de machine learning

• Jiang Wagner Mamani Lopez ^[2] ; Juliana Mery Bautista Lopez ^[2] ; Ignacio Aguaded ^[1]
  1. [1] Universidad de Huelva

     Universidad de Huelva

     Huelva, España

     
  2. [2] Universidad Nacional de San Agustín de Arequipa, Perú
• Localización: RISTI: Revista Ibérica de Sistemas e Tecnologias de Informação, ISSN-e 1646-9895, Nº. 57, 2025, págs. 3-18
• Idioma: español
• Títulos paralelos:
  • Predictive model for beneficiary households in cash transfer programs: a comparison of machine learning techniques
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    Los programas de transferencias monetarias son una herramienta clave para reducir la pobreza y mejorar el bienestar de los hogares vulnerables en países en desarrollo. Sin embargo, la correcta selección de beneficiarios sigue siendo un desafío. Este estudio evalúa distintas técnicas de machine learning para predecir la participación del programa Juntos en Perú, empleando datos de la Encuesta Nacional de Hogares (ENAHO) del 2023. Se compararon modelos como regresión logística, árboles de decisión, máquina de soporte vectorial, gradient boosting machine, bosque aleatorio, LightGBM, XGBoost y CatBoost. Los resultados muestran que XGBoost presenta el mejor desempeño en la clasificación de beneficiarios. Estos hallazgos resaltan el potencial de las técnicas de machine learning para fortalecer la asignación de recursos en programas sociales. Su implementación impulsaría la modernización de la gestión pública, permitiendo una gestión de recursos económicos fundamentada en datos.

  • English

    Cash transfer programs are a key tool for reducing poverty and improving the well-being of vulnerable households in developing countries. However, the accurate selection of beneficiaries remains a challenge. This study evaluates different machine learning techniques to predict participation in the Juntos program in Peru, using data from the 2023 National Household Survey (ENAHO). Models such as logistic regression, decision trees, support vector machine, gradient boosting machine, random forest, LightGBM, XGBoost, and CatBoost were compared. The results show that XGBoost achieves the best performance in beneficiary classification. These findings highlight the potential of machine learning techniques to enhance the allocation of resources in social programs. Their implementation would drive the modernization of public management, enabling data-driven economic resource management.

• Referencias bibliográficas
  • Abhishek, K., & Abdelaziz, M. (2023). Machine Learning for Imbalanced Data: Tackle imbalanced datasets using machine learning and deep...
  • Aiken, E. L., Bedoya, G., Blumenstock, J. E., & Coville, A. (2023). Program targeting with machine learning and mobile phone data: Evidence...
  • Autenrieth, M., Levine, R. A., Fan, J., & Guarcello, M. A. (2021). Stacked ensemble learning for propensity score methods in observational...
  • Banerjee, A., & Duflo, E. (2019). Good Economics for Hard Times: Better Answers to Our Biggest Problems (1st Ed.). Public Affairs.
  • Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
  • Breiman, L., Friedman, J., Olshen, R. A., & Stone, C. J. (1984). Introduction To Tree Classification. En J. Kimmel & A. Cava (Eds.)....
  • Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD International Conference on...
  • Chen, T. S. (2018). Evaluating Conditional Cash Transfer Policies with Machine Learning Methods. https://arxiv.org/abs/1803.06401
  • Crespo, C. (2020). Two become one: Improving the targeting of conditional cash transfers with a predictive model of school dropout. Economia,...
  • Corporación Andina de Fomento. (2018). Programas de transferencias monetarias condicionadas de dinero en efectivo: ¿solución mágica para mejorar...
  • Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273–297. https://doi.org/10.1007/BF00994018
  • Dietrich, S., Malerba, D., & Gassmann, F. (2024). Predicting social assistance beneficiaries: On the social welfare damage of data biases....
  • Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189 – 1232. https://doi.org/10.1214/ aos/1013203451
  • Gardner, J. R., Kusner, M. J., Xu, Z. E., Weinberger, K. Q., & Cunningham, J. P. (2014). Bayesian optimization with inequality constraints....
  • Goller, D., Lechner, M., Moczall, A., & Wolff, J. (2020). Does the estimation of the propensity score by machine learning improve matching...
  • Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Interpretation of the Fitted Logistic Regression Model. In D. Balding, N. A....
  • Goldstein, I. M. Johnstone, G. Molenberghs, D. W. Scott, A. F. M. Smith, R. S. Tsay & S. Weisberg (ed.). Applied Logistic Regression (pp....
  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting...
  • Lee, B. K., Lessler, J., & Stuart, E. A. (2010). Improving propensity score weighting using machine learning. Statistics in Medicine,...
  • Linden, A., & Yarnold, P. R. (2018). Estimating causal effects for survival (time-to-event) outcomes by combining classification tree...
  • Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation Forest. In 2008 Eighth IEEE International Conference on Data Mining, (pp. 413–422)....
  • Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing...
  • Maciel, F. A., & Duarte, D. (2023). The impact of cash transfer participation on unhealthy consumption in Brazil. Health Policy OPEN,...
  • McBride, L., & Nichols, A. (2018). Retooling poverty targeting using out-of-sample validation and machine learning. World Bank Economic...
  • Nufus, R. D. S., Susetyo, B., & Sartono, B. E.. (2024). Exploring the Potential Impact of Ginger Consumption on the Duration of COVID-19...
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel V. Thirion, B., Grisel, O., Blondel, M., Prettenhofer P. Weiss, R., Dubourg, V., Vanderplas,...
  • Peñarreta, M., & Armas, R. (2024). Educación financiera en jóvenes universitarios ecuatorianos: Una aplicación de Machine Learning. RISTI...
  • Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). Catboost: Unbiased boosting with categorical features....
  • Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. In Information Processing...
  • Tito, A. E. A., Condori, B. O. H., & Vera, Y. P. (2023). Comparative analysis of Machine Learning Techniques for the prediction of cases...
  • Tu, C. (2019). Comparison of various machine learning algorithms for estimating generalized propensity score. Journal of Statistical Computation...
  • Watkins, S., Jonsson-Funk, M., Brookhart, M. A., Rosenberg, S. A., O’Shea, T. M., & Daniels, J. (2013). An empirical comparison of tree-based...
  • Zhao, P., Su, X., Ge, T., & Fan, J. (2016). Propensity score and proximity matching using random forest. Contemporary Clinical Trials,...