EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Integrasi Machine Learning dengan Geographically Weighted Regression untuk Analisis Indeks Pembangunan Manusia

Ismi Rizqa Lina, Dia Cahya Wati, Ibnu Mansyur Hamdani, Yulia Resti

METIK Jurnal · 30.06.2026 · 10 (1) · 148-158

DOI: 10.47002/nakv4774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift METIK Jurnal, online erschienen am 30.06.2026. Verfasst von Ismi Rizqa Lina und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The success of national development is determined not only by economic growth but also by the quality of human development, which is measured through the Human Development Index (HDI). Although Indonesia's HDI has continued to improve, regional disparities in Western Indonesia remain a significant development challenge. This study aims to classify and analyze the factors influencing HDI by integrating the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Geographically Weighted Regression (GWR) methods with adaptive Gaussian weighting. Class imbalance in the training data was addressed using the Synthetic Minority Oversampling Technique (SMOTE), while model performance was evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The results show that SVM with a Radial Basis Function (RBF) kernel outperformed KNN, achieving an accuracy of 78.8%, a precision of 0.89, a recall of 0.78, and an F1-score of 0.82. In comparison, KNN achieved an accuracy of 76.9%, a precision of 0.89, a recall of 0.76, and an F1-score of 0.80. Furthermore, the GWR analysis identified 16 spatial clusters characterized by different dominant factors, including population size, the Community Literacy Development Index, per capita expenditure, the open unemployment rate, and the number of sub-districts. The GWR model produced a coefficient of determination (R²) of 84.17%, indicating strong explanatory power. These findings demonstrate that the integration of machine learning techniques and GWR is effective in classifying HDI and revealing spatial variations in human development factors, providing valuable insights for the formulation of more targeted development policies aimed at reducing regional HDI disparities.

Zitieren

APA

Lina, I. R., Wati, D. C., Hamdani, I. M., & Resti, Y. (2026). Integrasi Machine Learning dengan Geographically Weighted Regression untuk Analisis Indeks Pembangunan Manusia. METIK Jurnal, 10(1), 148-158. https://doi.org/10.47002/nakv4774

Vancouver

Lina IR, Wati DC, Hamdani IM, Resti Y. Integrasi Machine Learning dengan Geographically Weighted Regression untuk Analisis Indeks Pembangunan Manusia. METIK Jurnal. 2026;10(1):148-158. doi:10.47002/nakv4774

BibTeX
@article{Lina2026,
  author = {Lina, Ismi Rizqa and Wati, Dia Cahya and Hamdani, Ibnu Mansyur and Resti, Yulia},
  title = {Integrasi Machine Learning dengan Geographically Weighted Regression untuk Analisis Indeks Pembangunan Manusia},
  journal = {METIK Jurnal},
  year = {2026},
  volume = {10},
  number = {1},
  pages = {148--158},
  doi = {10.47002/nakv4774}
}
Kostenlos starten →