Klasifikasi Kualitas Karet Menggunakan Metode Random Forest Pada Perusahaan XYZ
Company XYZ, a crumb rubber processor in Sumatra, Indonesia, assigns each production lot a Low, Medium, or High quality category by laboratory testing, but recorded parameters are not linked to them. This study tests how well Random Forest reproduces the categories from six parameters in 1,031 lots, only 13.5% of which are Low. Random Forest was compared with Support Vector Machine (SVM), Decision Tree, and two naive baselines using hold-out, repeated, and nested cross-validation. Cross-validated macro-F1 of the tuned Random Forest was 0.409, higher than Decision Tree (0.365; p = 0.028) and not significantly different from SVM (0.385; p = 0.13), yet only slightly above random guessing (0.330). No model exceeded the accuracy of always guessing High (0.507), and the Low class fared worst (F1 about 0.23). The six parameters barely differ between classes, so the data carry little class information. The model suits only flagging lots for laboratory re-testing.
Authors
- Hardini Novianti
- Ken Ditha Tania
- Mira Afrina (ORCID: https://orcid.org/0009-0000-1461-5338)
- Alsella Meiriza
- Ongki Juliandra
Institutions
- Sriwijaya University (ID)
Publication Details
- Journal
- Jurnal Manajemen dan Teknologi
- Published
- 2026-11-18
- DOI
- https://doi.org/10.63447/jmt.v3i2.2195
- Primary Topic
- Data Mining and Machine Learning Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00