Pengelompokan Perusahaan Perbankan Berdasarkan Rasio Keuangan Menggunakan Metode Kohonen Som Dan Klasifikasi Artificial Neural Network

Setiawan, Michelle Citra Amanda (2023) Pengelompokan Perusahaan Perbankan Berdasarkan Rasio Keuangan Menggunakan Metode Kohonen Som Dan Klasifikasi Artificial Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06311940000073-Undergraduate_Thesis.pdf] Text
06311940000073-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2025.

Download (2MB) | Request a copy

Abstract

Pandemi Covid-19 mengakibatkan penurunan ekonomi di berbagai dunia akibat ditutupnya seluruh sektor untuk mencegah penularan virus yang lebih masif. Kontraksi pertumbuhan ekonomi membuat persentase kredit macet meningkat yang dapat menyebabkan perusahaan Perbankan mengalami kenaikan likuiditas dan menurunnya profitabilitas dalam jangka panjang dapat menyebabkan perusahaan mengalami kebangkrutan. Dalam periode 2020-2022, terdapat 17 Bank BPR yang telah mengalami likuidasi dan 19 perusahaan Perbankan lainnya terancam “merger”. Oleh karena itu, penelitian ini mengangkat topik financial distress pada perusahaan perbankan menggunakan metode pengelompokan Kohonen Self-Organized Map (SOM) dilanjut analisis klasifikasi Artificial Neural Network (ANN) untuk mengetahui kondisi keuangan perusahaan Perbankan ke dalam kategori financial distress atau non-financial distress. Data yang digunakan bersumber dari Bursa Efek Indonesia (BEI) dengan menggunakan 10 rasio keuangan yang dihitung dari laporan keuangan tahunan tahun 2021. Hasil pengelompokan perusahaan Perbankan menggunakan Kohonen SOM dengan 2 cluster adalah 41 perusahaan Perbankan dalam cluster 1 yang teridentifikasi sebagai perusahaan dengan financial distress dan 4 perusahaan Perbankan dalam cluster 2 yang teridentifikasi sebagai perusahaan dengan non-financial distress. Kemudian hasil pengelompokan perusahaan disimpulkan memiliki perbedaan karakter antar cluster dengan menggunakan metode MANOVA. Selanjutnya dilakukan analisis klasifikasi menggunakan metode ANN dengan Backpropagation dimana hasil ketepatan klasifikasi yang didapatkan sangat tinggi yaitu 92,31%
=========================================================================================================================================
The Covid-19 pandemic has caused economic decline in many parts of the world due to the closure of all sectors to prevent more massive transmission of the virus. The contraction of economic growth makes the percentage of bad debts increase which can cause Banking companies to experience increased liquidity and decreased profitability in the long run can cause the company to experience bankruptcy. In the period 2020-2022, there are 17 BPR Banks that have been liquidated and 19 other Banking companies are threatened with "mergers". Therefore, this research raises the topic of financial distress in banking companies using the Kohonen Self-Organized Map (SOM) clustering method followed by Artificial Neural Network (ANN) classification analysis to determine the financial condition of banking companies into the category of financial distress or non-financial distress. The data used is sourced from the Indonesia Stock Exchange (IDX) using 10 financial ratios calculated from the 2021 annual financial statements. The results of grouping Banking companies using Kohonen SOM with 2 clusters are 41 Banking companies in cluster 1 identified as companies with financial distress and 4 Banking companies in cluster 2 identified as companies with non-financial distress. Then the results of grouping companies are concluded to have differences in character between clusters using the MANOVA method. Furthermore, classification analysis is carried out using the ANN method with Backpropagation where the classification accuracy results obtained are very high at 92.31%

Item Type: Thesis (Other)
Uncontrolled Keywords: ANN, Financial Distress, Kohonen SOM, Rasio Keuangan, Perbankan, ANN, Banking, Financial Distress, Financial Ratio, Kohonen SOM
Subjects: Q Science > Q Science (General) > Q325.78 Back propagation
Q Science > QA Mathematics
Q Science > QA Mathematics > QA278.55 Cluster analysis
Divisions: Faculty of Mathematics, Computation, and Data Science > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User: Michelle Citra Amanda Setiawan
Date Deposited: 06 Jul 2023 07:36
Last Modified: 06 Jul 2023 07:42
URI: http://repository.its.ac.id/id/eprint/98348

Actions (login required)

View Item View Item