Prediksi Financial Distress Bank Umum Di Indonesia Menggunakan Support Vector Machine

Maulana, Muhammad Alfin (2025) Prediksi Financial Distress Bank Umum Di Indonesia Menggunakan Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043211026-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Perbankan adalah sektor mayoritas dalam industri keuangan yang memegang peranan penting dalam sistem keuangan di Indonesia. Sektor perbankan di Indonesia telah mengalami beberapa krisis keuangan baik dalam skala regional, nasional maupun internasional. Perbankan nasional pernah mengalami penurunan yang sangat signifikan saat terjadi krisis ekonomi dan moneter di tahun 1998. Rentannya perbankan terguncang akan permasalahan menjadi perhatian khusus bagi negara mengingat perbankan merupakan salah satu sektor vital bagi negara. Otoritas jasa keuangan (OJK) akan menetapkan suatu bank sebagai bank dalam resolusi jika bank mengalami kesulitan keuangan dan membahayakan kelangsungan usahanya serta tidak dapat disehatkan. Kriteria bank termasuk dalam status-status tersebut dapat terlihat dari rasio keuangan dari bank. Prediksi terhadap kebangkrutan bank menjadi salah satu bentuk early warning system yang merupakan salah satu langkah preventif terhadap permasalahan ekonomi yang lebih luas. Hasil penelitian menunjukkan bahwa jumlah bank umum yang mengalami financial distress menunjukkan tren menurun dari tahun 2020 hingga 2023. Berdasarkan pemilihan metode terbaik menunjukkan bahwa metode Support Vector Machine (SVM) dengan optimasi Particle Swarm Optimization (PSO) menggunakan data hasil penanganan imbalance class dengan metode Synthetic Minority Over-Sampling Technique (SMOTE) yang menghasilkan performa yang paling baik dalam mendeteksi financial distress pada bank umum di Indonesia. Variabel dengan pengaruh paling besar terhadap model prediksi financial distress bank umum di Indonesia BOPO dan ROE. Selain itu, aplikasi berbasis dashboard uang dikembangkan menggunakan Streamlit memungkinkan pengguna untuk mendeteksi dini kondisi keuangan bank umum di indonesia
====================================================================================================================================
Banking is the dominant sector in the financial industry and plays a crucial role in Indonesia's financial system. The Indonesian banking sector has experienced several financial crises, both regionally, nationally, and internationally. National banking experienced a significant decline during the 1998 economic and monetary crisis. The vulnerability of banks to these challenges is a particular concern for the state, given that banking is a vital sector. The Financial Services Authority (OJK) will designate a bank as under resolution if it experiences financial difficulties that threaten its business continuity and cannot be restored to health. The criteria for banks to qualify for these statuses can be seen from their financial ratios. Predicting bank bankruptcy serves as an early warning system, a preventative measure against broader economic problems. The results of the study indicate that the number of commercial banks experiencing financial distress shows a downward trend from 2020 to 2023. Based on the selection of the best method, it shows that the Support Vector Machine (SVM) method with Particle Swarm Optimization (PSO) optimization using data from class imbalance handling with the Synthetic Minority Over-Sampling Technique (SMOTE) method produces the best performance in detecting financial distress in commercial banks in Indonesia. The variables with the greatest influence on the financial distress prediction model for commercial banks in Indonesia are BOPO and ROE. In addition, a money dashboard-based application developed using Streamlit allows users to detect the financial condition of commercial banks in Indonesia early.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Perbankan, Financial Distress, Particle Swarm Optimization (PSO), Support Vector Machine (SVM).
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Muhammad Alfin Maulana
Date Deposited:	21 Jul 2025 07:13
Last Modified:	21 Jul 2025 07:13
URI:	http://repository.its.ac.id/id/eprint/120314

Actions (login required)

View Item