Penerapan Fitur Seleksi dan Particle Swarm Optimization pada Algoritma Support Vector Machine  untuk Analisis Credit Scoring

Abdul Razak Naufal; Akrim Teguh Suseno

doi:10.47065/josyc.v5i1.4409

Abdul Razak Naufal ITSNU Pekalongan, Pekalongan, Indonesia
Akrim Teguh Suseno * ITSNU Pekalongan, Pekalongan, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/josyc.v5i1.4409

Keywords: Feature Selection; PSO; SVM; Credit Scoring; Cooperative

Abstract

After the Covid-19 pandemic, the banking sector faced significant challenges in contributing to achieving national goals in terms of increasing living standards and equalizing the regional economy. Hundreds of millions of low-income people have no credit or bank accounts because they do not have sufficient credit history to warrant the credit scores assigned to them. An estimated 1.7 billion people (31% of the adult population) do not have an account with a financial institution. People today are usually concentrated in developing countries, especially in China 204 million, India 357 million and Indonesia 102 million people. Because it is very difficult to make accurate predictions in determining credit worthiness for low-income people. Cooperatives are financial institutions that have a crucial role in channeling financing to members and the community to develop their businesses. An inappropriate credit distribution process can have a negative effect on KSP, resulting in frequent losses. This risk is known as problem loans, the cause is the KSP's failure to analyze the credit of prospective debtors. Therefore, calculations are needed to detect opportunities for credit risk default by prospective debtors objectively and precisely so that loan problems do not occur. Credit scoring is a method used to evaluate credit risk in terms of loan applications from consumers [4]. In this research we will provide a solution using classification techniques with feature selection methods in the Particle Swarm Optimization (PSO) Algorithm and Support Vector Machine (SVM) to predict the credit risk of prospective debtors failing to make loan payments. The application of the SVM algorithm in credit scoring research is because SVM is good at data classification. However, the standard SVM model still does not produce optimal results due to the difficulty of determining the best parameters, therefore researchers will optimize it with the Feature Selection and PSO algorithms to determine the best parameters. The results from the combination of several parameters using PSO-SVM obtained an accuracy of 87.23%, therefore the application of this method was proven to improve the performance of the SVM algorithm to increase its accuracy results in predicting the feasibility of granting credit.

Downloads

Download data is not yet available.

References

D. B. Vukovic, K. Romanyuk, S. Ivashchenko, and E. M. Grigorieva, “Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression,” Expert Syst. Appl., vol. 194, no. January, p. 116553, 2022, doi: 10.1016/j.eswa.2022.116553.

R. Oktapiani, D. Prayudi, A. Fajria, N. S. Z. Nufus, and R. N. Lestari, “Sistem Pendukung Keputusan Untuk Menentukan Managemen Kelayakan Pemberian Kredit Di Bank Mandiri Taspen Sukabumi Menggunakan Metode Analytic Hierarchy Process,” Indones. J. Softw. Eng., vol. 8, no. 1, pp. 36–45, 2022, doi: 10.31294/ijse.v8i1.12054.

V. B. Djeundje, J. Crook, R. Calabrese, and M. Hamid, “Enhancing credit scoring with alternative data,” Expert Syst. Appl., vol. 163, p. 113766, 2021, doi: 10.1016/j.eswa.2020.113766.

M. Abdoli, M. Akbari, and J. Shahrabi, “Bagging Supervised Autoencoder Classifier for credit scoring,” Expert Syst. Appl., vol. 213, no. PB, p. 118991, 2023, doi: 10.1016/j.eswa.2022.118991.

S. Purnama and A. P. Kusumawardhani, “Deteksi Peluang Gagal Bayar Calon Debitur Menggunakan Algoritma Particle Swarm Optimization (PSO) untuk Meningkatkan Kinerja Manajemen Risiko pada Koperasi Simpan Pinjam ABC,” KUBIK J. Publ. Ilm. Mat., vol. 6, no. 2, pp. 71–84, 2022, doi: 10.15575/kubik.v6i2.13835.

H. Yasin, A. R. Hakim, and A. Hoyyi, “Sistem Informasi Potensi Kredit Macet Berbasis Aplikasi Credit Scoring-Support Vector Machine (CS-SVM),” Pros. Semin. Nas. VARIANSI, vol. 1, no. 1, pp. 1–9, 2020, [Online]. Available: https://ojs.unm.ac.id/variansistatistika/article/view/19493

A. Markov, Z. Seleznyova, and V. Lapshin, “Credit scoring methods: Latest trends and points to consider,” J. Financ. Data Sci., vol. 8, pp. 180–201, 2022, doi: 10.1016/j.jfds.2022.07.002.

S. Riyadi, M. M. Siregar, K. fadhli F. Margolang, and K. Andriani, “Analysis Of SVM And Naive Bayes Algorithm In Classification Of Nad Loans In Save And Loan Cooperatives,” JURTEKSI (Jurnal Teknol. dan Sist. Informasi), vol. 8, no. 3, pp. 261–270, Aug. 2022, doi: 10.33330/jurteksi.v8i3.1483.

S. Bumbungan, Kusrini, and Kusnawi, “Penerapan Particle Swarm Optimization (PSO) dalam Pemilihan Parameter Secara Otomatis pada Support Vector Machine (SVM) untuk Prediksi Kelulusan Mahasiswa Politeknik Amamapare Timika,” J. Tek. AMATA, vol. 4, no. 1, pp. 81–93, 2022, doi: 10.55334/jtam.v4i1.77.

G. Yao, X. Hu, and G. Wang, “A novel ensemble feature selection method by integrating multiple ranking information combined with an SVM ensemble model for enterprise credit risk prediction in the supply chain,” Expert Syst. Appl., vol. 200, no. January, p. 117002, 2022, doi: 10.1016/j.eswa.2022.117002.

D. T. Larose, Data Mining Methods and Models. Canada: John Wiley & Sons, Inc, 2007.

S. Maldonado, C. Bravo, J. López, and J. Pérez, “Integrated framework for profit-based feature selection and SVM classification in credit scoring,” Decis. Support Syst., vol. 104, pp. 113–121, 2017, doi: 10.1016/j.dss.2017.10.007.

J. Cervantes, F. Garcia-Lamont, L. Rodriguez, A. López, J. R. Castilla, and A. Trueba, “PSO-based method for SVM classification on skewed data sets,” Neurocomputing, vol. 228, no. December 2015, pp. 187–197, 2017, doi: 10.1016/j.neucom.2016.10.041.

C. W. Dawson, Projects in Computing and Information Systems. Addison Wesley, 2009.

P. Danenas and G. Garsva, “Selection of Support Vector Machines based classifiers for credit risk domain,” Expert Syst. Appl., vol. 42, no. 6, pp. 3194–3204, 2015, doi: 10.1016/j.eswa.2014.12.001.

A. R. Naufal, R. Satria, and A. Syukur, “Penerapan Bootstrapping untuk Ketidakseimbangan Kelas dan Weighted Information Gain untuk Feature Selection pada Algoritma Support Vector Machine untuk Prediksi Loyalitas Pelanggan,” J. Intell. Syst., vol. 1, no. 2, pp. 98–108, 2015.

A.- Amrin and O.- Pahlevi, “Implementation of Logistic Regression Classification Algorithm and Support Vector Machine for Credit Eligibility Prediction,” J. Informatics Telecommun. Eng., vol. 5, no. 2, pp. 433–441, 2022, doi: 10.31289/jite.v5i2.6220.

M. Han, J., & Kamber, Data Mining : Concepts and Techniques, 3nd Editio. Morgan Kaufmann Publishers, 2012.

G. N. Kouziokas, “SVM kernel based on particle swarm optimized vector and Bayesian optimized SVM in atmospheric particulate matter forecasting,” Appl. Soft Comput. J., vol. 93, p. 106410, 2020, doi: 10.1016/j.asoc.2020.106410.

S. Chen, J. qiang Wang, and H. yu Zhang, “A hybrid PSO-SVM model based on clustering algorithm for short-term atmospheric pollutant concentration forecasting,” Technol. Forecast. Soc. Change, vol. 146, no. May, pp. 41–54, 2019, doi: 10.1016/j.techfore.2019.05.015.

M. A. Witten, I. H., Frank, E., & Hall, Data Mining Practical Machine Learning Tools and Techniques, 3rd ed. USA: Morgan Kaufmann Publishers, 2011.

T. T. Muryono, A. Taufik, and I. Irwansyah, “Perbandingan Algoritma K-Nearest Negihbor, Decision Tree, dan Naive Bayes untuk Menentukan Kelayakan Pemberian Kredit,” Infotech J. Technol. Inf., vol. 7, no. 1, pp. 35–40, Jun. 2021, doi: 10.37365/jti.v7i1.104.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Penerapan Fitur Seleksi dan Particle Swarm Optimization pada Algoritma Support Vector Machine untuk Analisis Credit Scoring