Prediksi Financial Distress Menggunakan Artificial Neural Network pada Perusahaan Sektor Consumer Cyclicals di Bursa Efek Indonesia

Tantowi, Axel Jonathan (2024) Prediksi Financial Distress Menggunakan Artificial Neural Network pada Perusahaan Sektor Consumer Cyclicals di Bursa Efek Indonesia. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003201138-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Pertumbuhan sektor Consumer Cyclicals, terutama dalam industri pariwisata dan rekreasi, menghadapi tantangan signifikan karena perubahan tren konsumen dan faktor eksternal yang cepat berubah. Penelitian ini bertujuan untuk memprediksi financial distress pada perusahaan sektor Consumer Cyclicals menggunakan metode Artificial Neural Network (ANN) dengan periode dinamis k=1 selama 2 periode (2021-2022). Sampel penelitian melibatkan 103 perusahaan yang dipilih berdasarkan kriteria tertentu. Data rasio keuangan tahun 2021 digunakan sebagai fitur, sementara klasifikasi financial distress tahun 2022 digunakan sebagai target. Hasil analisis menunjukkan bahwa perusahaan yang mengalami financial distress cenderung memiliki rasio keuangan negatif, terutama pada rasio profitabilitas, rasio leverage, rasio aktivitas, dan rasio pasar. Selain itu, terdapat variasi yang lebih besar dalam rasio keuangan perusahaan yang berada dalam kondisi financial distress dibandingkan dengan perusahaan yang tidak mengalami financial distress. Model ANN terbaik untuk prediksi financial distress adalah skema tanpa teknik SMOTE dan menggunakan feature selection FCBF, terdiri dari ANN (9-2-1) dengan optimizer SGD Momentum dan learning rate sebesar 0,1. Prediksi kondisi financial distress perusahaan sektor Consumer Cyclicals pada tahun 2023 menunjukkan bahwa 54 perusahaan diprediksi akan mengalami financial distress, sementara 49 perusahaan diprediksi tidak mengalami financial distress.
=========================================================================================================
The growth of the Consumer Cyclicals sector, especially in the tourism and recreation industry, faces significant challenges due to rapidly changing consumer trends and external factors. This research aims to predict financial distress in companies within the Consumer Cyclicals sector using the Artificial Neural Network (ANN) method with a dynamic period of k=1 over 2 periods (2021-2022). The research sample involved 103 companies selected based on certain criteria. Financial ratio data from 2021 was used as features, while the classification of financial distress in 2022 was used as the target. The analysis results show that companies experiencing financial distress tend to have negative financial ratios, particularly in profitability ratios, leverage ratios, activity ratios, and market ratios. Additionally, there is greater variation in the financial ratios of companies in financial distress compared to companies not experiencing financial distress. The best ANN model for predicting financial distress is a scheme without using the SMOTE technique and utilizing the FCBF feature selection, consisting of ANN (9-2-1) with an SGD Momentum optimizer and a learning rate of 0.1. Predictions for the financial distress condition of Consumer Cyclicals sector companies in 2023 indicate that 54 companies are predicted to experience financial distress, while 49 companies are predicted not to experience financial distress.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Artificial Neural Network, Consumer Cyclicals, FCBF, Financial Distress, SMOTE, Artificial Neural Network, Consumer Cyclicals, FCBF, Financial Distress, SMOTE
Subjects:	H Social Sciences > HC Economic History and Conditions > HC441 Macroeconomics. H Social Sciences > HC Economic History and Conditions > HC60.M34 Technical assistance. H Social Sciences > HC Economic History and Conditions > HC79.E5 Sustainable development. (circular economy) H Social Sciences > HG Finance Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Axel Jonathan Tantowi
Date Deposited:	08 Aug 2024 05:11
Last Modified:	08 Aug 2024 05:11
URI:	http://repository.its.ac.id/id/eprint/114410

Actions (login required)

View Item