Perbandingan Algoritma Machine Learning Untuk Prediksi Gagal Bayar Pinjaman Koperasi yang Optimal
DOI:
https://doi.org/10.22441/format.2024.v13.i2.001Keywords:
accuracy, decision tree, default prediction, f1-score, k-nearest neighbors, knn, logistic regression, precision, random forest, recallAbstract
Abstract - Predicting loan repayment defaults is quite an important thing to do in a financial institution such as a Savings and Loans Cooperative. The aim is to minimize the occurrence of loan defaults by borrowers to cooperatives so that bankruptcy does not occur. In this study, the development of a predictive model was carried out using several popular machine learning algorithms, namely logistic regression, decision tree, random forest and k-nearest neighbors (KNN), then the four models were compared and evaluated in order to find out which model with the most effective algorithm. in predicting loan defaults in cooperatives. Program evaluation is carried out by metrics such as accuracy, precision, recall, and f1-score. The dataset itself is obtained from a loan list which includes attributes such as borrower profile, loan amount, number of installments, etc. This dataset is divided into training data and test data to train and evaluate the model. The results showed that the Random Forest algorithm model provided the best accuracy, reaching 89%, followed by the Decision Tree with the highest accuracy value, which reached 84%, and finally Logistic Regression and K-Nearest Neighbors with the same accuracy value, namely 81%. These four algorithms were chosen because they are well-known algorithms among other algorithms for financial predictions because of their ability to understand complex relationships, provide interpretable results, overcome overfitting problems, and consider the interrelationships between similar entities.Abstrak – Melakukan prediksi kegagalan pembayaran pinjaman merupakan hal yang cukup penting untuk dilakukan di sebuah badan keuangan seperti Koperasi Simpan Pinjam. Tujuannya yaitu untuk meminimalisir terjadinya gagal bayar pinjaman oleh peminjam kepada Koperasi agar tidak terjadi bangkrut. Pada penelitian ini dilakukan pengembangan model prediksi dengan menggunakan beberapa algoritma machine learning yang cukup popular yaitu logistic regression, decision tree, random forest dan k-nearest neighbors (KNN), kemudian keempat model tersebut dibandingkan dan dievaluasi agar diketahui model dengan algoritma mana yang paling efektif dalam memprediksi gagal bayar pinjaman di Koperasi. Evaluasi program dilakukan metrik-metrik seperti akurasi, presisi, recall, dan f1-score. Untuk datasetnya sendiri didapat dari daftar pinjaman yang mencakup atribut seperti profil peminjam, jumlah pinjaman, banyak angsuran, dll. Dataset ini dibagi menjadi data pelatihan dan data uji untuk melatih dan mengevaluasi model. Hasil penelitian menunjukkan bahwa model algoritma Random Forest memberikan akurasi terbaik yaitu mencapai 89%, diikuti oleh Decision Tree dengan nilai akurasi tertingginya yang mencapai 84%, dan yang terakhir Logistic Regression dan K-Nearest Neighbors dengan nilai akurasi yang sama yaitu 81%. Keempat algoritma ini dipilih karena merupakan algoritma yang cukup terkenal di antara algoritma lainnya untuk prediksi dalam hal keuangan karena kemampuan mereka untuk memahami hubungan yang kompleks, memberikan hasil yang dapat diinterpretasikan, mengatasi masalah overfitting, dan mempertimbangkan keterkaitan antara entitas yang serupa.
Downloads
References
Andi Nursyahriana, Michael Hadjat, Irsan Tricahyadinata, “ANALISIS FAKTOR PENYEBAB TERJADINYA KREDIT MACET”, Forum Ekonomi: Jurnal Ekonomi, Manajemen dan Akuntansi Volume 19, No. 1, 2017
Sukri Syafudin, Ranu Agastya Nugraha, Kartika Handayani, Windu Gata, Safitri Linawati, “PREDIKSI STATUS PINJAMAN BANK DENGAN DEEP LEARNING NEURAL NETWORK (DNN)”, Jurnal Teknik Komputer AMIK BSI Volume 7, No.2, Juli 2021
Peter Martey Addo, Dominique Guegan, Bertrand Hassan, “CREDIT RISK ANALYSIS USING MACHINE AND DEEP LEARNING MODELS”, University Ca' Foscari of Venice, Dept. of Economics Research Paper Series No. 08/WP/ 2018
Kadek Dwi Pradnyana, Raden Aswin Rahadi, et al.,"LOAN DEFAULT PREDICTION IN MICROFINANCE GROUP LENDING WITH MACHINE LEARNING," International Journal of Business and Technology Management, Vol.4, No. 4, 83-95, 2022, 31 December 2022
Lkhagvadorj Munkhdalai, Tsendsuren Munkhdalai, Oyun-Erdene Namsrai, Jong Yun Lee, and Keun Ho Ryu, et al., "AN EMPIRICAL COMPARISON OF MACHINE-LEARNINGMETHODS ON BANK CLIENT CREDIT ASSESSMENTS," MDPI, 29 January 2019
Lin Zhua, Dafeng Qiua, Daji Ergua, Cai Yinga, Kuiyi Liu, “A STUDY ON PREDICTING LOAN DEFAULT BASED ON THE RANDOM FOREST ALGORITHM,” 7th International Conference on Information Technology and Quantitative Managemet, 2019
Aida Krichene Abdelmoula, “BANK CREDIT RISK ANALYSIS WITH K-NEARESTNEIGHBOR CLASSIFIER: CASE OF TUNISIAN BANKS” Accounting and Management Information Systems Vol. 14, No. 1, pp. 79-106, 2015
Laura Maria Badea Stroie, “TECHNIQUES FOR CUSTOMER BEHAVIOUR PREDICTION: A CASESTUDY FOR CREDIT RISK ASSESSMENT” New Techniques and Technologies for Statistics, 2013
Khandani, Amir E., Adlar J. Kim, and Andrew W. Lo, “CONSUMER CREDIT-RISK MODELS VIA MACHINE-LEARNING ALGORITHMS” Journal of Banking & Finance 34, 2010
Downloads
Published
How to Cite
Issue
Section
License
The copyright to this article is transferred to Universitas Mercu Buana (UMB) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UMB. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that this paper has not been published in the same form elsewhere.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above-mentioned paper as a whole to UMB. The copyright transfer covers the right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
Our Articles are licensed under CC BY-NC

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.