TIF_E41253310/Backend/Model/data/processed/clustering_summary.txt

32 lines
997 B
Plaintext

============================================================
CLUSTERING SUMMARY
Tanggal: 2026-08-28 04:27:42
============================================================
[MODEL INFO]
K = 4 (sesuai PRD)
Inertia: 893.89
Silhouette Score: 0.1034
Total Samples: 1114
Total Features: 500
[EVALUATION RESULTS]
K=2: Inertia=992.52, Silhouette=0.0595
K=3: Inertia=937.51, Silhouette=0.0833
K=4: Inertia=893.89, Silhouette=0.1034
K=5: Inertia=868.63, Silhouette=0.1151
K=6: Inertia=854.48, Silhouette=0.1154
[CLUSTER DISTRIBUTION]
Cluster 0: 587 (52.7%)
Cluster 1: 146 (13.1%)
Cluster 2: 183 (16.4%)
Cluster 3: 198 (17.8%)
[TOP TERMS PER CLUSTER]
Cluster 0: perintah, bumn, bnpp, jember, staff
Cluster 1: kerja, freelance, kerja lepas, lepas, freelance kerja
Cluster 2: wiraswasta, wiraswasta usaha, usaha sendiri, sendiri, usaha
Cluster 3: swasta, usaha swasta, usaha, staff, indonesia
============================================================