Comparative Analysis of Artificial Neural Networks, Linear Regression, Random Forest, and Support Vector Machine for Predicting Poverty Levels in Indonesia
DOI:
https://doi.org/10.59395/ijadis.v6i3.1467Keywords:
Backpropagation, Poverty Prediction, Deep Learning, Model Evaluation, Artificial Neural Network, Linear Regression, Random Forest, Support Vector MachineAbstract
Poverty remains a persistent and complex challenge in Indonesia, driven by multiple interrelated socioeconomic factors. Accurate poverty prediction is essential to support effective policy formulation and targeted interventions. This study evaluates and compares the performance of four machine learning models for predicting poverty levels in Indonesia: Artificial Neural Networks (ANN), Linear Regression, Random Forest, and Support Vector Machine (SVM). A quantitative approach is employed using provincial-level data from 2015 to 2023, consisting of 306 observations and 13 socioeconomic indicators related to education, employment, health, infrastructure, and economic conditions. Data preprocessing includes data cleaning, Min–Max normalization, and feature selection. Model performance is assessed using Mean Squared Error (MSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The results show that ANN achieves the best predictive performance, with the lowest MSE (0.0132) and MAE (0.0815), and the highest R² value (0.924). Random Forest and SVM demonstrate competitive performance, while Linear Regression yields the weakest accuracy. These findings confirm the effectiveness of ANN for poverty prediction and support its use in data-driven poverty reduction policies in Indonesia.
Downloads
References
[1] Badan Pusat Statistik (BPS), Profil Kemiskinan di Indonesia, Jakarta, Indonesia: BPS, 2023.
[2] World Bank, Indonesia Poverty Assessment: Pathways to Economic Security, Washington, DC, USA: World Bank, 2022.
[3] A. Alkire and J. Foster, “Multidimensional poverty measurement and analysis,” Oxford Poverty & Human Development Initiative, Oxford, U.K., 2016.
[4] United Nations Development Programme (UNDP), Human Development Report 2023/2024, New York, NY, USA: UNDP, 2024.
[5] Asian Development Bank, Poverty, Vulnerability, and Inequality in Indonesia, Manila, Philippines: ADB, 2021.
[6] S. Haughton and S. R. Khandker, Handbook on Poverty and Inequality, Washington, DC, USA: World Bank, 2018.
[7] R. Kanbur, “The challenges of regional poverty analysis,” World Development, vol. 122, pp. 47–58, 2019.
[8] J. A. Nelder and R. W. Wedderburn, “Generalized linear models and their limitations in complex socioeconomic data,” Statistical Science, vol. 31, no. 2, pp. 165–178, 2016.
[9] M. Jordan and T. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science, vol. 349, no. 6245, pp. 255–260, 2015. DOI: https://doi.org/10.1126/science.aaa8415
[10] C. Mullainathan and J. Spiess, “Machine learning: An applied econometric approach,” Journal of Economic Perspectives, vol. 31, no. 2, pp. 87–106, 2017. DOI: https://doi.org/10.1257/jep.31.2.87
[11] S. Haykin, Neural Networks and Learning Machines, 3rd ed., Upper Saddle River, NJ, USA: Pearson, 2016.
[12] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, Cambridge, MA, USA: MIT Press, 2016.
[13] L. Zhang, P. Wang, and H. Li, “Nonlinear modeling of socioeconomic indicators using artificial neural networks,” Expert Systems with Applications, vol. 159, pp. 113–128, 2020.
[14] A. Nugroho, R. F. Malik, and D. Sari, “Challenges of poverty data modeling in Indonesia: A regional perspective,” Journal of Asian Economics, vol. 68, pp. 101–114, 2020.
[15] G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, 2nd ed., New York, NY, USA: Springer, 2021. DOI: https://doi.org/10.32614/CRAN.package.ISLR2
[16] OECD, Data-Driven Policy Making for Inclusive Growth, Paris, France: OECD Publishing, 2020.
[17] R. Pratama, S. Hidayat, and A. Wibowo, “Artificial neural network modeling for demographic and poverty analysis at subdistrict level,” Indonesian Journal of Geography, vol. 54, no. 2, pp. 215–226, 2022.
[18] D. Puspitasari and M. R. Saputra, “Prediction of poor population in Indonesia using backpropagation neural network,” TELKOMNIKA (Telecommunication, Computing, Electronics and Control), vol. 18, no. 6, pp. 3125–3132, 2020.
[19] F. Ramadhan, A. Setiawan, and L. Kurniawati, “Provincial-level poverty rate forecasting using neural network models,” Procedia Computer Science, vol. 216, pp. 624–633, 2023.
[20] Chen, M. Alvarez, and S. Kumar, “Multidimensional poverty modeling using ANN regression: Evidence from developing countries,” Social Indicators Research, vol. 172, pp. 1–24, 2024.
[21] M. K. Rafiei and A. H. Nematollahi, “Comparative analysis of machine learning methods for poverty prediction,” Applied Artificial Intelligence, vol. 35, no. 9, pp. 701–720, 2021.
[22] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed., New York, NY, USA: Springer, 2017.
[23] K. Murphy, Machine Learning: A Probabilistic Perspective, Cambridge, MA, USA: MIT Press, 2018.
[24] Ministry of National Development Planning (BAPPENAS), National Strategy for Poverty Reduction, Jakarta, Indonesia, 2022.
[25] Kaggle, Indonesia Poverty Statistics (BPS), 2024. [Online]. Available: https://www.kaggle.com
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Lia Alfia, Fresy Nugroho, Yunifa Miftachul Arif
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
Share
Plum Analytics