ZAI, WITARLINA (2026) ANALISIS PROFIL PROGRAM BANTUAN SOSIAL MENGGUNAKAN K-MEANS DENGAN METODOLOGI CRISP-DM (STUDI KASUS: DESA BENGLE, KABUPATEN KARAWANG). S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (1MB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab I Pendahuluan.pdf Restricted to Registered users only Download (104kB) |
|
|
Text (BAB II)
Bab II Tinjauan Pustaka.pdf Restricted to Registered users only Download (301kB) |
|
|
Text (BAB III)
Bab III Metode Penelitian.pdf Restricted to Registered users only Download (762kB) |
|
|
Text (BAB IV)
Bab IV Hasil dan Pembahasan.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB V)
Bab V Saran dan Kesimpulan.pdf Restricted to Registered users only Download (200kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (301kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (955kB) |
Abstract
The targeting accuracy of social assistance programs at the village level remains a challenge because village officials struggle to systematically evaluate program coverage. This study aims to apply the K-Means Clustering algorithm with the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology to analyze demographic profiles and the coverage of three social assistance programs (PKH, Sembako, and PBI-JK) in Bengle Village, Majalaya Subdistrict, Karawang Regency. The dataset consists of 1,074 residents obtained by integrating the RT-level 2024 population data with the 2026 DTSEN database through NIK matching, resulting in 773 residents registered in DTSEN (72.0%). Six demographic attributes were used as clustering features after preprocessing with LabelEncoder and StandardScaler. The optimal number of clusters was determined using a combination of the Elbow Method and Silhouette Score. The results yielded k = 6 with a Silhouette Score of 0.5767 (strong structure category) and an inertia of 1,084.37. The six clusters formed include Senior Male Household Heads (3.26%), Female Teenagers (15.64%), Housewives (27.56%), Male Toddlers (16.11%), Male Private Employees (24.21%), and Male Teenagers (13.22%). Coverage analysis against eligible residents based on welfare deciles shows PKH coverage of 9.8%, Sembako 11.0%, and PBI-JK 61.3%. PKH and Sembako recipients are concentrated in the Housewives cluster (75.0% and 77.8%, respectively), while three clusters of adult and adolescent males have no PKH or Sembako recipients despite containing eligible residents. The analysis results are implemented in an interactive Streamlit-based dashboard with four main pages and a drill-down feature, designed to support a hierarchical reporting flow from the RT Head, RW Head, to the Village Head. This research is intended for monitoring and coverage Evaluation, not for determining the eligibility of individual recipients. Keywords: K-Means Clustering, CRISP-DM, Social Assistance, DTSEN, Dashboard, Bengle Village. Ketepatan sasaran program bantuan sosial di tingkat desa masih menjadi tantangan karena perangkat desa kesulitan mengevaluasi cakupan program secara sistematis. Penelitian ini bertujuan menerapkan algoritma K-Means Clustering dengan metodologi Cross-Industry Standard Process for Data Mining (CRISP-DM) untuk menganalisis profil kependudukan dan cakupan tiga program bantuan sosial (PKH, Sembako, dan PBI-JK) di Desa Bengle, Kecamatan Majalaya, Kabupaten Karawang. Data yang digunakan mencakup 1.074 penduduk hasil integrasi data kependudukan tingkat RT tahun 2024 dengan data DTSEN tahun 2026 melalui pencocokan NIK, menghasilkan 773 penduduk terdaftar DTSEN (72,0%). Enam atribut demografis digunakan sebagai fitur clustering setelah preprocessing dengan LabelEncoder dan StandardScaler. Jumlah klaster optimal ditentukan menggunakan kombinasi Metode Elbow dan Silhouette Score. Hasil penelitian memperoleh k = 6 dengan Silhouette Score 0,5767 (kategori strong structure) dan inertia 1.084,37. Enam klaster yang terbentuk meliputi Kepala Keluarga Senior Laki-laki (3,26%), Anak-Remaja Perempuan (15,64%), Ibu Rumah Tangga (27,56%), Balita Laki-laki (16,11%), Karyawan Swasta Laki-laki (24,21%), dan Anak-Remaja Laki-laki (13,22%). Analisis cakupan bantuan sosial terhadap penduduk eligible berdasarkan desil kesejahteraan menunjukkan cakupan PKH 9,8%, Sembako 11,0%, dan PBI-JK 61,3%. Konsentrasi penerima PKH dan Sembako berada pada klaster Ibu Rumah Tangga (75,0% dan 77,8%), Sementara itu, klaster laki-laki dewasa dan anak-remaja tidak memiliki penerima PKH maupun Sembako meskipun terdapat penduduk eligible. Hasil analisis diimplementasikan pada dashboard interaktif berbasis Streamlit dengan empat halaman utama dan fitur drill-down, yang dirancang mendukung alur pelaporan bertingkat dari Ketua RT, Ketua RW, hingga Kepala Desa. Penelitian ini bersifat monitoring dan evaluasi cakupan, bukan penentuan kelayakan individu penerima bantuan sosial. Kata Kunci: K-Means Clustering, CRISP-DM, Bantuan Sosial, DTSEN, Dashboard, Desa Bengle.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41822110006 |
| Uncontrolled Keywords: | K-Means Clustering, CRISP-DM, Bantuan Sosial, DTSEN, Dashboard, Desa Bengle. |
| Subjects: | 300 Social Science/Ilmu-ilmu Sosial > 360 Social Problems and Services/Permasalahan dan Kesejahteraan Sosial > 363 Other Social Problems and Services/Masalah dan Layanan Sosial Lainnya > 363.9 Population Problems/Permasalahan Kependudukan 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | khalimah |
| Date Deposited: | 05 Oct 2026 16:28 |
| Last Modified: | 05 Oct 2026 16:28 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/104268 |
Actions (login required)
 |
View Item |
