Random Forest-Based Poverty Forecasting Using Socioeconomic Indicators in Bangka Belitung Islands Province
Arcitech: Journal of Computer Science and Artificial Intelligence · 27.06.2026 · 6 (1) · 202-218
DOI: 10.29240/arcitech.v6i1.17171 ↗Kurz gefasst
Fachartikel in der Zeitschrift Arcitech: Journal of Computer Science and Artificial Intelligence, online erschienen am 27.06.2026. Verfasst von Burham Isnanto und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Poverty remains a significant socioeconomic challenge in the Bangka Belitung Islands Province, Indonesia, where economic dependence on tin mining and plantation commodities creates structural vulnerabilities that influence regional welfare conditions. Poverty remains a significant socioeconomic challenge in the Bangka Belitung Islands Province, Indonesia, where economic dependence on tin mining and plantation commodities creates structural vulnerabilities that influence regional welfare conditions. Previous poverty forecasting studies in Indonesia have predominantly employed statistical and econometric models, which are often limited in modeling non-linear socioeconomic interactions and are rarely validated using subnational panel data. Consequently, the potential of machine learning techniques, particularly Random Forest, for poverty prediction at the regency and municipal level remains underexplored. This study addresses this gap by developing a Random Forest-based poverty prediction model using socioeconomic indicators from 2019–2025. This study proposes a machine learning approach to predict poverty rates using the Random Forest algorithm implemented in Altair AI Studio (RapidMiner). Panel data covering the period 2019–2025 were collected from official publications of Badan Pusat Statistik (BPS) Bangka Belitung Islands Province. Three socioeconomic indicators were used as predictor variables: the Human Development Index (HDI), Open Unemployment Rate (OUR), and the number of poor people in each regency or municipality. The dataset consists of 49 observations representing seven administrative regions across seven years. The developed Random Forest model achieved an R² value of 0.800, an RMSE of 0.722, and an MAE of 0.561, demonstrating good predictive accuracy. The validated model was subsequently used to estimate poverty rates for 2026, producing predictions ranging from 2.762% to 6.244%. These findings highlight the potential of machine learning techniques to support poverty forecasting and evidence-based regional development policies.
Zitieren
APA
Isnanto, B., & Sulaiman, R. (2026). Random Forest-Based Poverty Forecasting Using Socioeconomic Indicators in Bangka Belitung Islands Province. Arcitech: Journal of Computer Science and Artificial Intelligence, 6(1), 202-218. https://doi.org/10.29240/arcitech.v6i1.17171
Vancouver
Isnanto B, Sulaiman R. Random Forest-Based Poverty Forecasting Using Socioeconomic Indicators in Bangka Belitung Islands Province. Arcitech: Journal of Computer Science and Artificial Intelligence. 2026;6(1):202-218. doi:10.29240/arcitech.v6i1.17171
BibTeX
@article{Isnanto2026,
author = {Isnanto, Burham and Sulaiman, Rahmat},
title = {Random Forest-Based Poverty Forecasting Using Socioeconomic Indicators in Bangka Belitung Islands Province},
journal = {Arcitech: Journal of Computer Science and Artificial Intelligence},
year = {2026},
volume = {6},
number = {1},
pages = {202--218},
doi = {10.29240/arcitech.v6i1.17171}
}
EUVIMED