Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Eksponensial REKADATA (Rekayasa Data dan Kecerdasan Artifisial)
Nariza Wanti Wulan Sari
Mulawarman University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Energy Engineering Mathematics Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Klasterisasi Rumah Tangga Miskin di Kota Samarinda Menggunakan Algoritma K-Modes dengan Validasi Klaster Davies Bouldin Index Memi Nor Hayati; Nihayatul Khoiriyah; Nariza Wanti Wulan Sari; Aji Syarif Hidayatullah
EKSPONENSIAL Vol. 17 No. 1 (2026): Jurnal Eksponensial
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/eksponensial.v17i1.1627

Abstract

Poverty alleviation is one of goals at Sustainable Development Goals (SDGs) that can be supported by grouping poor households based on similar characteristics, enabling social assistance programs to be delivered more effectively and accurately. This study aims to cluster poor households in Samarinda City using the K-Modes algorithm with validation through the Davies-Bouldin Index (DBI). The data were obtained from the 2023 Samarinda Poverty Survey and consist of 16 poor households indicators. The analysis was conducted by testing the number of clusters (K) from 2 to 10. The results indicate that the optimal number of clusters is 3, with a DBI value of 1.6997. Cluster 1 consists of 11,237 households, Cluster 2 consists of 2,327 households, and Cluster 3 consists of 1,451 households. The distinct characteristics of each cluster suggest that the clustering results can serve as a basis for designing more targeted social assistance programs. Future research is recommended to consider alternative clustering methods for categorical data, such as the ROCK algorithm, which utilizes link-based similarity by considering the number of common neighbors between objects, allowing it to better capture the inherent structure of categorical data compared to distance-based methods.
Application of Random Forest with SMOTE and Random Search for Food Security Classification in Indonesia Susi Hasriani; Nariza Wanti Wulan Sari; Pratama Yuly Nugraha; M Fathurahman; Meiliyani Siringoringo
REKADATA Vol. 2 No. 1 (2026): Rekayasa Data dan Kecerdasan Artifisial (REKADATA)
Publisher : CV Mazaya Cahaya Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Food security is an important aspect of sustainable development and one of the key priorities of the Sustainable Development Goals (SDGs). Differences in food security conditions across regencies and cities in Indonesia require accurate classification to support the identification of vulnerable regions and appropriatepolicy-making. The random forest method is a classification method with good predictive performance, which can be improved through hyperparameter optimization using random search. However, its classification performance may decline when applied to imbalanced datasets. Therefore, the Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance. This study aimed to classify the food security levels ofregencies and cities in Indonesia in 2024 using random forest with SMOTE and random search hyperparameter optimization and to evaluate model performance based on accuracy, precision, recall, and F1-score. The data were obtained from the Food Security and Vulnerability Atlas (FSVA), comprising 514 regencies and cities, with food security level as the response variable and eight predictor variables. The dataset was divided into training andtesting sets using proportions of 80:20 and 90:10. SMOTE was applied with K = 5, while random search was conducted using 20 hyperparameter combinations to determine the optimal model. The results showed that the 80:20 data partition outperformed the 90:10 partition, achieving an accuracy of 88.35%, precision of 83.33%, recall of 50.00%, and F1-score of 62.50%. The best model correctly classified 10 food-insecure and 81 food-secure regencies and cities. These findings provide information for identifying regions based on food security levels and support more targeted food security policy-making. 
Co-Authors Aji Syarif Hidayatullah M Fathurahman Meiliyani Siringoringo Memi Nor Hayati Nihayatul Khoiriyah Pratama Yuly Nugraha Susi Hasriani