Article Per Year (5 Year)
p-Index From 2020 - 2025
4.846
P-Index
This Author published in this journals
All Journal BIMASTER Epsilon: Jurnal Matematika Murni dan Terapan Jurnal Matematika Sains dan Teknologi JMPM: Jurnal Matematika dan Pendidikan Matematika Jurnal Pengabdian kepada Masyarakat Nusantara Euler : Jurnal Ilmiah Matematika, Sains dan Teknologi Jurnal Forum Analisis Statistik STATISTIKA
Shantika Martha
Universitas Tanjungpura
Agriculture, Biological Sciences & Forestry Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Mathematics Social Sciences Transportation Other

Published : 50 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Matematika Sains dan Teknologi

 1 
Implementation of Random Oversampling Technique in the K-Nearest Neighbor Method for Creditworthiness Analysis Ayu Dhita Putri Wulandari; Shantika Martha; Wirda Andani
Jurnal Matematika Sains dan Teknologi Vol. 25 No. 1 (2024)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v25i1.4909.2024

Abstract

Banks are financial institutions, one of whose main activities is providing credit to their customers. The existence of credit granting activities requires the bank to know the feasibility of prospective debtors in receiving credit. Because in practice, credit granting activities still often have bad credit problems. The problem of bad credit can be overcome by analyzing the feasibility of granting credit to prospective debtors. The data used in this study consists of 10 independent variables and 1 dependent variable is collectibility (kol). The collectibility (col) data consists of 500 data for the current debtor class and 26 data for the non-current debtor class, this indicates an imbalance class. So in this study, the application of the random oversampling (ROS) technique is used to overcome the imbalance class with the K-Nearest Neighbor (KNN) method in classifying current and non-current debtor data. ROS was chosen because it can generally provide better results and does not eliminate information from existing data. The analysis results obtained show that the use of the KNN method with the application of ROS is better than the KNN model without ROS, with an accuracy of 84.91% at data testing. The KNN model with ROS can improve the model's ability to classify noncurrent debtor data or the specificity value of the model increases by 25%. In the KNN model without ROS the model cannot classify non-current debtor data correctly at all, this can endanger the bank in making decisions.
Co-Authors Anggi Putri Dewi Anita Anita Ayu Dhita Putri Wulandari Bartolomius Bartolomius Bella Amalia David Jordy Dhandio Desa Ayu Natalia Dwi Marisa Midyanti Dwi Setiaji Eka Wahyuning Dhewanty Enis Rahayu Evy Sulistianingsih Fahiza Syanaya Fajri Anugrah Pratiwi Fery Prastio Fransisca Febrianti Sundari Hayati Hayati Hendra Perdana Hidayatun Nisa Ika Ayu Krismawanti Ika Novira Zulianti Indah Noviyanti Julianti Kastari Kunti Wijayanti Laksono Trisnantoro Lidia Karnelia Luh Putu Ratna Sundari Mariatul Kiftiah Marisi Aritonang Maya Rosalina Mega Putri Muhammad Septian Muthiara Anantha Simanjuntak Nanda Shalsadilla Naomi N. Debataraja Naomi Nessyana Debataraja Neva Satyahadewi Nova Andaresta Nurfitri Imro’ah Nurul Qomariyah NUR’AINUL MIFTAHUL HUDA Rizky Oktaviani Putri Santi Santi Selvy Putri Agustianto Setyo Wir Rizki Setyo Wira Rizki Silvana Rika Siti Aprizkiyandari, Nurul Qomariyah, Shantika Martha, Sri Jumiati Sriyana Sriyana Suaibah Suaibah Sumiarti Sumiarti Supandi Supandi Susanti Susanti Sutro Sutro Syarifah Zela Hafizah Tamtama, Ray Thariq Thariq Vina Annisa Nurdiani Aji Vita Virgianti Wahyudio Hariadi Warzuqna Olyan Wirda Andani Yogi Pratama Yosi Yosi Yude Anggreni Yundari, Yundari Yundari, Yundari