<![CDATA[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.]]>
Copyrights © 2025
