Claim Missing Document
Check
Articles

Found 3 Documents
Search

Data-Driven Insights Into Underdeveloped Regencies: SHAP-Based Explainable Artificial Intelligence Approach Oktora, Siskarossa Ika; Matualage, Dariani; Notodiputro, Khairil Anwar; Sartono, Bagus
International Journal of Artificial Intelligence Research Vol 9, No 1 (2025): June
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v9i1.1399

Abstract

Classification analysis in high-dimensional data presents significant challenges, particularly due to the presence of complex non-linear patterns that traditional methods, such as logistic regression, fail to capture effectively. This limitation is often reflected in relatively low model accuracy. One approach to addressing this issue is through machine learning-based classification methods, such as Random Forest and Support Vector Machine (SVM). While these models generally achieve higher accuracy than logistic regression, their black-box nature limits interpretability, making it difficult to explain their classification decisions. As machine learning models continue to advance, interpretability has become a crucial concern, especially in data-driven decision-making. Post-hoc explainable artificial intelligence (XAI) techniques offer a viable solution to enhance model transparency. This study applies SHAP to machine learning models to gain insights into the underdevelopment status of regencies in Indonesia. The results indicate that SVM outperforms both logistic regression and Random Forest. SHAP values estimated from SVM, using various permuted variable subsets, exhibit stability. Clustering analysis identifies five optimal clusters of underdeveloped regencies. Based on average SHAP values, underdevelopment alleviation strategies should focus on social factors (Cluster 1), infrastructure (Cluster 2), accessibility (Cluster 3), and a combination of infrastructure, accessibility, education, and healthcare (Cluster 4), while Cluster 5 requires improvements in accessibility and economic conditions.
STRATEGY FOR ELIMINATING NEGLECTED TROPICAL DISEASES THROUGH INDIVIDUAL AND AREA ASPECTS USING THE HIERARCHICAL LOGISTIC REGRESSION METHOD Oktora, Siskarossa Ika; Matualage, Dariani; Amalia Pasaribu, Asysta; Fitriyani Sahamony, Nur; Kurnia, Anang
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 19 No 4 (2025): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol19iss4pp2495-2506

Abstract

Filariasis is one of the Neglected Tropical Diseases (NTDs) that is often associated with poverty and marginalized community groups. Papua is the province with the highest number of chronic filariasis cases and has the largest number of endemic districts/municipalities compared to other provinces in Indonesia. Papua is also the province with the highest poverty rate in Indonesia. To support the government's filariasis elimination program, this study aims to determine variables that influence the incidence of filariasis in Papua at the individual and area levels. This study uses 2018 Indonesia Basic Health Research data from the Ministry of Health and regional data from BPS-Statistics Indonesia. The results using Hierarchical Binary Logistic Regression concluded that defecation behavior in latrines, prevention behavior against mosquito bites, participation in mass preventive drug administration, number of poor people, and number of health workers have a significant effect on the incidence of filariasis. In contrast, the variables age, gender, type of work, and level of education do not have a significant effect.
Penerapan Regresi Data Panel pada Faktor-faktor yang Mempengaruhi Tingkat Kemiskinan di Provinsi Papua Barat Tahun 2018-2022 Malawat, Jihan Rahmi; Matualage, Dariani; Matulessy , Esther Ria
LITERATUS Jurnal Ilmiah Internasional Sosial dan Budaya
Publisher : Neolectura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37010/lit.v6i1.1676

Abstract

West Papua has consistently been one of the regions with the highest poverty rates in Indonesia, ranking second in 2022. This study investigates the factors influencing the poverty rate in West Papua from 2018 to 2022 using panel data analysis, which combines both cross-sectional and time-series data. The variables examined include the open unemployment rate, economic growth rate, and human development index. A Random Effect Model (REM) was selected as the most appropriate model for analyzing the data, given its ability to account for individual-specific effects while assuming that these effects are uncorrelated with the independent variables. The model produced a goodness of fit of 0.74, suggesting a strong explanatory power. The results indicate that the economic growth rate and human development index significantly influence the poverty rate, both showing a negative correlation with poverty levels. However, the open unemployment rate was found to be insignificant. These findings suggest that focusing on economic growth and improving human development outcomes could be key to reducing poverty in West Papua. Policy implications and recommendations for further research are also discussed.