Prediksi Financial Distress pada Perusahaan Sektor Consumer Cyclicals di Bursa Efek Indonesia Menggunakan Support Vector Machine

Azzahra, Andini Maritza (2025) Prediksi Financial Distress pada Perusahaan Sektor Consumer Cyclicals di Bursa Efek Indonesia Menggunakan Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5003211104-Undergraduate_Thesis.pdf] Text
5003211104-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only

Download (4MB) | Request a copy

Abstract

Sektor Consumer Cyclicals mencakup perusahaan yang memproduksi atau mendistribusikan produk dan jasa yang sangat dipengaruhi oleh siklus ekonomi, seperti kendaraan penumpang, pakaian, barang rumah tangga, dan jasa pariwisata. Adanya delisting yang dialami beberapa perusahaan sektor ini dapat terjadi karena perusahaan tersebut berada dalam kondisi financial distress. Financial distress merujuk pada ketidakmampuan perusahaan untuk memenuhi kewajiban finansialnya yang dapat mengarah pada kebangkrutan. Oleh karena itu, prediksi financial distress sangat penting untuk memberikan sistem peringatan dini dan mengantisipasi kerugian. Penelitian ini bertujuan untuk memberikan gambaran umum perusahaan sektor Consumer Cyclicals dan untuk memprediksi financial distress menggunakan Support Vector Machine (SVM). Data yang digunakan dalam penelitian ini berupa rasio keuangan yang diambil dari laporan keuangan konsolidasian perusahaan sektor Consumer Cyclicals yang terdaftar di Bursa Efek Indonesia (BEI). Klasifikasi financial distress didasarkan pada nilai Earnings Per Share (EPS) yang negatif selama dua tahun berturut-turut. Hasil penelitian menunjukkan bahwa perusahaan financial distress memiliki Debt to Assets Ratio (DAR), Debt to Equity Ratio (DER), dan Total Assets Turnover (TATO) yang lebih tinggi, sedangkan perusahaan non-financial distress memiliki Current Ratio (CR), Return on Assets (ROA), Return on Equity (ROE), dan Net Profit Margin (NPM) yang lebih tinggi. Model SVM terbaik diperoleh dengan hyperparameter C=2^7=128 dan γ=2^(-1)=0.5 dengan rata-rata akurasi 88,09%, precision 78,00%, recall 85,71%, F1-Score 79,49%, dan AUC ROC 94,85%. Prediksi pada tahun 2024 menunjukkan terdapat 38 perusahaan diprediksi mengalami financial distress dan 88 perusahaan diprediksi tidak mengalami financial distress.
====================================================================================================================================
The Consumer Cyclicals sector includes companies that produce or distribute products and services that are highly influenced by economic cycles, such as passenger vehicles, clothing, household goods, and tourism services. The delisting experienced by several companies in this sector can occur because these companies are in a condition of financial distress. Financial distress refers to a company's inability to fulfill its financial obligations, which can lead to bankruptcy. Therefore, predicting financial distress is crucial to provide an early warning system and anticipate potential losses. This study aims to provide an overview of companies in the Consumer Cyclicals sector and to predict financial distress using the Support Vector Machine (SVM) method. The data used in this research consist of financial ratios derived from the consolidated financial statements of Consumer Cyclicals companies listed on the Indonesia Stock Exchange (IDX). The classification of financial distress is based on negative Earnings Per Share (EPS) for two consecutive years. The results show that financially distressed companies have higher Debt to Assets Ratio (DAR), Debt to Equity Ratio (DER), and Total Assets Turnover (TATO), while non-financially distressed companies have higher Current Ratio (CR), Return on Assets (ROA), Return on Equity (ROE), and Net Profit Margin (NPM). The best SVM model was obtained with hyperparameters C=2^7=128 and γ=2^(-1)=0.5, achieving an average accuracy of 88.09%, precision of 78.00%, recall of 85.71%, F1-Score of 79.49%, and ROC AUC of 94.85%. Predictions for 2024 indicate that 38 companies are predicted to experience financial distress, while 88 companies are predicted to be non-financially distressed.

Item Type: Thesis (Other)
Uncontrolled Keywords: Financial Distress, Prediksi, Rasio Keuangan, Support Vector Machine (SVM), Financial Distress, Financial Ratio, Prediction, Support Vector Machine (SVM)
Subjects: H Social Sciences > HG Finance
Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Andini Maritza Azzahra
Date Deposited: 01 Aug 2025 09:19
Last Modified: 01 Aug 2025 09:19
URI: http://repository.its.ac.id/id/eprint/126197

Actions (login required)

View Item View Item