Kunardi, Carinn (2024) Perbandingan metode ann dan mda untuk memprediksi financial distress pada perusahaan sektor perindustrian di Indonesia = Comparison of ann and mda methods for predicting financial distress in industrial sector companies in Indonesia. Bachelor thesis, Universitas Pelita Harapan.
Text (Title)
Title.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Abstract)
Abstract.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (ToC)
ToC.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Chapter1)
Chapter1.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Chapter2)
Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Chapter3)
Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Chapter4)
Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB) |
|
Text (Chapter5)
Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Bibliography)
Bibliography.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
Text (Appendices)
Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB) |
Abstract
Gejolak dalam perekonomian suatu negara dapat memengaruhi performa keuangan perusahaan hingga menyebabkan kebangkrutan. Dalam periode tahun 2019 hingga 2021, terdapat 13 perusahaan di-delisting dari Bursa Efek Indonesia (BEI). Penelitian ini bertujuan untuk mengatasi tantangan dalam memprediksi potensi kebangkrutan perusahaan industri di Indonesia dengan melakukan prediksi terhadap financial distress. Data yang digunakan dalam penelitian ini adalah data keuangan perusahaan yang dikumpulkan dari 24 perusahaan sektor perindustrian terpilih yang sejak tahun 2002 hingga 2023 terdaftar di Bursa Efek Indonesia (BEI). Data yang digunakan adalah data kuartal sejak kuartal pertama 2002 hingga kuartal keempat 2023. Prediksi financial distress akan dilakukan menggunakan metode artificial neural network (ANN) dan multiple discriminant analysis (MDA). Model ANN dan MDA akan dirancang untuk mendapatkan konfigurasi optimal dengan menggunakan variasi parameter seperti variabel independen, jumlah unit node, hidden layer, dan activation function. Berdasarkan konfigurasi parameter dalam model, akan dianalisis performance metrics terbaik masing-masing dari setiap model. Model ANN menunjukkan tingkat kinerja yang sangat baik dalam melakukan prediksi dengan F1-score sebesar 99,15%. Di sisi lain, model MDA memiliki F1-score yang lebih rendah, yaitu sebesar 80,27%. Dengan demikian, dapat disimpulkan bahwa model-model ANN memiliki performa prediksi yang lebih baik dalam memprediksi kondisi financial distress pada perusahaan industri di Indonesia dibandingkan dengan model-model MDA. / The volatility in the economy of a country can affect the financial performance of companies, leading to bankruptcy. During the period from 2019 to 2021, 13 companies were delisted from the Indonesia Stock Exchange (IDX). This research aims to address the challenges in predicting the potential bankruptcy of industrial companies in Indonesia by forecasting financial distress. The data used in this study are financial data collected from 24 selected industrial sector companies listed on the Indonesia Stock Exchange (IDX) from 2002 to 2023. The data used are quarterly data from the first quarter of 2002 to the fourth quarter of 2023. The prediction of financial distress will be conducted using artificial neural network (ANN) and multiple discriminant analysis (MDA) methods. ANN and MDA models will be designed to obtain optimal configurations by varying parameters such as independent variables, number of nodes, hidden layers, and activation functions. Based on the parameter configurations in the models, the best performance metrics of each model will be analyzed. The ANN model shows excellent performance in prediction with an F1-score of 99.15%. On the other hand, the MDA model has a lower F1-score, which is 80.27%. Thus, it can be concluded that ANN models have better predictive performance in predicting financial distress conditions in industrial companies in Indonesia compared to MDA models.
Item Type: | Thesis (Bachelor) | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Creators: |
|
||||||||||||
Contributors: |
|
||||||||||||
Uncontrolled Keywords: | financial distress; artificial neural network; multiple discriminant analysis; data keuangan; hyperparameter tuning. | ||||||||||||
Subjects: | Q Science > QA Mathematics | ||||||||||||
Divisions: | University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics |
||||||||||||
Depositing User: | Carinn Kunardi | ||||||||||||
Date Deposited: | 19 Jul 2024 07:08 | ||||||||||||
Last Modified: | 19 Jul 2024 07:08 | ||||||||||||
URI: | http://repository.uph.edu/id/eprint/64150 |
Actions (login required)
View Item |