Prediksi Financial Distress Perusahaan Asuransi Jiwa di Indonesia dengan Metode Support Vector Machine, Generalized Extreme Value Regression, dan Logistic Regression

Ramadhani, Sekar Wulan (2022) Prediksi Financial Distress Perusahaan Asuransi Jiwa di Indonesia dengan Metode Support Vector Machine, Generalized Extreme Value Regression, dan Logistic Regression. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06211840000094-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (64MB) | Request a copy

Abstract

Perusahaan asuransi sebagai salah satu lembaga keuangan memegang peranan penting dalam pembangunan ekonomi. Perlu dilakukan manajemen risiko agar perusahaan tidak mengalami masalah keuangan perusahaan, seperti penurunan kondisi keuangan (financial distress), yang kemudian dapat menyebabkan kebangkrutan perusahaan. Penelitian ini bertujuan untuk memprediksi financial distress perusahaan asuransi jiwa di Indonesia dengan metode Support Vector Machine (SVM), Generalized Extreme Value Regression (GEVR), dan Logistic Regression. Analisis dilakukan dengan mempertimbangkan time window dan seleksi variabel. Berdasarkan nilai akurasi dan AUC, model terbaik secara serentak diperoleh dengan metode GEVR pada size 0 dan 2, logistic regression pada size 1, dan SVM pada size 3. Sementara model terbaik dengan seleksi variabel diperoleh dengan metode GEVR pada seluruh size data. Secara umum, skenario terbaik dalam memprediksi financial distress adalah dengan menggunakan stepwise GEVR. Hasil yang diperoleh yaitu rasio keuangan yang berpengaruh signifikan pada hampir semua pemodelan dengan menggunakan size data yang berbeda adalah rasio cadangan teknis.
==============================================================================================================================
Insurance companies as financial institutions play an essential role in economic development. It is necessary to carry out risk management so that it does not experience financial problems, such as financial distress, which can lead to a company's bankruptcy. This study aims to predict the financial distress condition of life insurance companies in Indonesia using Support Vector Machine (SVM), Generalized Extreme Value Regression (GEVR), and Logistic Regression methods. The analysis was carried out considering the time window and variable selection. Based on the accuracy and AUC values, the best simultaneous model was obtained using the GEVR method at sizes 0 and 2, logistic regression at size 1, and SVM at size 3. Meanwhile, the best model with variable selection was obtained using the GEVR method for all data sizes. In general, the best model to predict financial distress was obtained using stepwise GEVR. The financial ratio that significantly affects almost all models using different data sizes is the technical reserves ratio.

Item Type:	Thesis (Other)
Additional Information:	RSSt 519.536 Ram p-1 2022
Uncontrolled Keywords:	Asuransi Jiwa, Financial Distress, Generalized Extreme Value Regression, Logistic Regression, Support Vector Machine. Financial Distress, Generalized Extreme Value Regression, Life Insurance, Logistic Regression, Support Vector Machine.
Subjects:	H Social Sciences > HA Statistics
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	11 Jun 2026 04:22
Last Modified:	11 Jun 2026 04:22
URI:	http://repository.its.ac.id/id/eprint/133732

Actions (login required)

View Item