Predicting Social Assistance Recipient Eligibility Using the Explainable Boosting Machine Algorithm on Demographic Data

Authors

  • Silvy Handayani Maharaja Universitas Muhammadiyah Sumatera Utara, Medan, Indonesia
  • Hevlie Winda Nazry S Universitas Muhammadiyah Sumatera Utara, Medan, Indonesia

DOI:

https://doi.org/10.35335/jmirte.v5i2.403

Keywords:

Explainable Boosting Machine (EBM), social assistance, machine learning, demographic data, eligibility prediction

Abstract

This study aims to predict the eligibility of social assistance recipients using an Explainable Boosting Machine (EBM) algorithm based on demographic data. The main problem in social assistance distribution is inaccurate targeting, which leads to inclusion and exclusion errors due to simple and inaccurate selection methods. This study employed a quantitative approach with supervised learning on 500 demographic data sets covering variables such as income, employment, education, and number of dependents. The data underwent preprocessing, including labeling, transformation, and balancing using SMOTE, resulting in a total dataset of 924 data points. The model was then divided into 80% training data and 20% testing data. The results showed that the EBM model achieved very high performance, with accuracy, precision, recall, and F1-score values each reaching 100%. Furthermore, EBM was able to interpret the contribution of each variable in determining recipient eligibility. Thus, this model is not only accurate but also transparent, supporting more objective, effective, and accountable decision-making in social assistance distribution.

References

Alahmadi, R., Almujibah, H., Alotaibi, S., Elshekh, A. E. A., Alsharif, M., & Bakri, M. (2023). Explainable Boosting Machine: A Contemporary Glass-Box Model to Analyze Work Zone-Related Road Traffic Crashes. Safety, 9(4), 1–15. https://doi.org/10.3390/safety9040083

Arslan, A. K., Yagin, F. H., Algarni, A., Al-hashem, F., & Paolo, L. (2024).

Combining the Strengths of the Explainable Boosting Machine and Metabolomics Approaches for Biomarker Discovery in Acute Myocardial Infarction.

Artha, D. P., & Misdawita. (2023). Ekonomi dan Kebijakan Publik Indonesia Keywords. Jurnal Ekonomi Dan Kebijakan Publik Indonesia, 10(1), 65–80.

Damuri, A., Riyanto, U., Rusdianto, H., & Aminudin, M. (2021). Implementasi Data Mining dengan Algoritma Naïve Bayes Untuk Klasifikasi Kelayakan Penerima Bantuan Sembako. JURIKOM (Jurnal Riset Komputer), 8(6), 219. https://doi.org/10.30865/jurikom.v8i6.3655

Jatipaningrum, M. T., Azhari, S. E., & Suryowati, K. (2022). Pengelompokan Kabupaten Dan Kota Di Provinsi Jawa Timur Berdasarkan Tingkat Kesejahteraan Dengan Metode K-Means Dan Density-Based Spatial Clustering Of Applications With Noise. Jurnal Derivat: Jurnal Matematika Dan Pendidikan Matematika, 9(1), 70–81. https://doi.org/10.31316/j.derivat.v9i1.2832

Jurnal, H., Fathurohman FKIP, A., & Fisika, P. (2021). Machine Learning Untuk Pendidikan: Mengapa Dan Bagaimana. Jurnal Informatika Dan Teknologi Komputer, 1(3), 57–62.

Khattak, A., Zhang, J., Chan, P. W., Chen, F., & Almujibah, H. (2024).

Explainable Boosting Machine: A Contemporary Glass-Box Strategy for the Assessment of Wind Shear Severity in the Runway Vicinity Based on the Doppler Light Detection and Ranging Data. Atmosphere, 15(1), 1–20. https://doi.org/10.3390/atmos15010020

Kiss, O., Baker, F. C., Palovics, R., Dooley, E. E., Pettee Gabriel, K., & Nagata, J.M. (2024). Using explainable machine learning and fitbit data to investigate predictors of adolescent obesity. Scientific Reports, 14(1), 1–13. https://doi.org/10.1038/s41598-024-60811-2

Maxwell, A. E., Sharma, M., & Donaldson, K. A. (2021). Explainable boosting machines for slope failure spatial predictive modeling. Remote Sensing,

(24). https://doi.org/10.3390/rs13244991

Normah, Rifai, B., Vambudi, S., & Maulana, R. (2022). Analisa Sentimen Perkembangan Vtuber Dengan Metode Support Vector Machine Berbasis SMOTE. Jurnal Teknik Komputer AMIK BSI, 8(2), 174–180. https://doi.org/10.31294/jtk.v4i2

Of, E., Assistance, S., Eligibility, R., On, B., Of, N., Using, D., Fuzzy, T. H. E., & Approach, M. (2025). Evaluasi Kelayakan Penerima Bantuan Sosial BerdasarkanPenghasilan Dan Jumlah Tanggungan Dengan Pendekatan FuzzyMamdani. 1(2), 67–78.

Perhan, A. I., Yustiana, I., & Sanjaya, I. (2025). Implementation of Machine Learning Using Decision Tree Method for Social Assistance Recipient Classification. Bit-Tech, 8(1), 901–909. https://doi.org/10.32877/bt.v8i1.2755

Puspitasari, N., & Sitohang, F. K. S. (2023). Pengolahan Data Demografi Penduduk Menggunakan Microsoft Excel di Kelurahan Sempaja Timur, Kota Samarinda. JAPI (Jurnal Akses Pengabdian Indonesia), 7(3), 181–190. https://doi.org/10.33366/japi.v7i3.3774

Setya, F., Sri, I., Zahra, M., Kristian, M., Jasmina, Z., Studi Administrasi Pembangunan Negara, P., & STIA LAN Bandung, P. (2022). “My Nutera” Di Kelurahan Tamansari Bandung Digitalization of Equivalent Social Assistance With Innovation “My Nutera” in Tamansari Village, Bandung. SeTIA Mengabdi-Jurnal Pengabdian Kepada Masyarakat, 3(3), 55–62.

Sihombing, P. R., Muslianti, D., & Yunita. (2022). RETRACTION NOTICE TO “Apakah Dana Desa dan Fungsi Belanja APBD Mampu Mengatasi Kemiskinan di Indonesia?” Jurnal Ekonomi Dan Statistik Indonesia, 2(2), 236–243. https://doi.org/10.11594/jesi.02.02.12

Sri Wahyuni, W., & Prima Putra, F. (2025). Analisis Karakteristik Rumah Tangga Miskin Penerima Program Keluarga Harapan dan Penerima Keluarga Harapan Sekaligus Bantuan Pangan Non-Tunai di Indonesia. Jurnal Informatika Ekonomi Bisnis, 7(2), 141–147. https://doi.org/10.37034/infeb.v7i2.1112

Suyasa, I. M. G., Retnosari, L., & Taufiq, N. (2022). Tepatkah Program Bantuan Sosial dalam Pengentasan Kemiskinan di Indonesia? Salus Cultura: Jurnal Pembangunan Manusia Dan Kebudayaan, 4(1), 42–52. https://doi.org/10.55480/saluscultura.v4i1.156

Wicaksono, H., Riyanto, A., Darmawan, R., & Hidayat, M. F. (2025). Explainable

Downloads

Published

2026-10-16