Optimasi Model Machine Learning untuk Reduksi Kesalahan Klasifikasi Penerima BLT Berbasis Data Sosial-Ekonomi
Abstract
Penelitian ini bertujuan mengoptimalkan model machine learning untuk mereduksi kesalahan klasifikasi penerima Bantuan Langsung Tunai (BLT) berbasis data sosial-ekonomi di Kabupaten Soppeng. Penelitian menggunakan pendekatan kuantitatif dengan desain eksperimen komputasional. Dataset yang digunakan terdiri atas 300 data calon penerima BLT dengan 22 variabel, mencakup indikator sosial-ekonomi seperti pendapatan, pekerjaan, jumlah tanggungan, kondisi rumah, kepemilikan aset, status kerentanan, dan riwayat penerimaan bantuan sosial. Algoritma yang diuji meliputi Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbor, Naive Bayes, dan XGBoost. Proses optimasi dilakukan melalui prapemrosesan data, one-hot encoding, normalisasi, seleksi fitur, dan hyperparameter tuning. Evaluasi model menggunakan accuracy, precision, recall, F1-score, ROC-AUC, dan confusion matrix. Hasil penelitian menunjukkan bahwa Random Forest menjadi model terbaik dengan accuracy 0,9833, precision 1,0000, recall 0,9643, F1-score 0,9818, dan ROC-AUC 0,9900. Analisis confusion matrix menunjukkan hanya terdapat satu kesalahan klasifikasi berupa false negative dan tidak terdapat false positive. Temuan ini menunjukkan bahwa model machine learning yang dioptimalkan dapat mendukung klasifikasi penerima BLT secara lebih objektif, akurat, dan berbasis data
Downloads
References
Bifarin, O. O. (2023). Interpretable machine learning with tree-based shapley additive explanations: Application to metabolomics datasets for binary classification. PLOS ONE, 18(5), e0284315. https://doi.org/10.1371/journal.pone.0284315
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Burke, M., Driscoll, A., Lobell, D. B., & Ermon, S. (2021). Using satellite imagery to understand and promote sustainable development. Science, 371(6535), eabe8628. https://doi.org/10.1126/science.abe8628
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21(1), 6. https://doi.org/10.1186/s12864-019-6413-7
Ismail, S. (2025). Data Mining Klasifikasi Penduduk Miskin Menggunakan Metode Support Vektor Machine. Jurnal Ilmiah Sistem Informasi Dan Teknik Informatika (JISTI), 8(April), 142–152. https://doi.org/https://doi.org/10.57093/jisti.v8i1.283
Jean, N., Burke, M., Xie, M., Alampay Davis, W. M., Lobell, D. B., & Ermon, S. (2016). Combining satellite imagery and machine learning to predict poverty. Science, 353(6301), 790–794. https://doi.org/10.1126/science.aaf7894
McBride, L., & Nichols, A. (2018). Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning. The World Bank Economic Review, 32(3), 531–550. https://doi.org/10.1093/wber/lhw056
Muh. Ikhsan Amar, M. F. R. (2025). Analisis Model Klasifikasi Penerima Bantuan Langsung Tunai Menggunakan Algoritma Naive Bayes. Journal of Computer Engineering, System and Science, 10(2), 585–594.
Poulin, C., Trimmer, J., Press-Williams, J., Yachori, B., Khush, R., Peletz, R., & Delaire, C. (2022). Performance of a novel machine learning-based proxy means test in comparison to other methods for targeting pro-poor water subsidies in Ghana. Development Engineering, 7, 100098. https://doi.org/https://doi.org/10.1016/j.deveng.2022.100098
Probst, P., Wright, M. N., & Boulesteix, A.-L. (2019). Hyperparameters and tuning strategies for random forest. WIREs Data Mining and Knowledge Discovery, 9(3), e1301. https://doi.org/https://doi.org/10.1002/widm.1301
Suherman , Misveria Villa Waru, N. (2022). Perancangan Aplikasi Pendataan Bantuan Langsung Tunai ( BLT ) Berbasis Web Pada Kantor Desa Maccile Kecamatan Lalabata Kabupaten Soppeng. Jurnal Ilmiah Sistem Informasi Dan Teknik Informatika (JISTI), 5, 117–124.
Yeh, C., Perez, A., Driscoll, A., Azzari, G., Tang, Z., Lobell, D., Ermon, S., & Burke, M. (2020). Using publicly available satellite imagery and deep learning to understand economic well-being in Africa. Nature Communications, 11(1), 2583. https://doi.org/10.1038/s41467-020-16185-w
JISTI
