| DC 欄位 |
值 |
語言 |
| DC.contributor | 資訊管理學系在職專班 | zh_TW |
| DC.creator | 陳昆憲 | zh_TW |
| DC.creator | Kun-Hsien Chen | en_US |
| dc.date.accessioned | 2022-7-12T07:39:07Z | |
| dc.date.available | 2022-7-12T07:39:07Z | |
| dc.date.issued | 2022 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=108453006 | |
| dc.contributor.department | 資訊管理學系在職專班 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 企業繼續經營假設是企業財務報表編制重大假設之一。現今企業所面臨的挑戰越來越多元，尤其在2008年的金融海嘯、2020年新型冠狀病毒COVID-19席捲全球的重大衝擊下，企業更加容易面臨爆發財務危機甚至會因此瀕臨倒閉的風險。然而普遍市場投資人及其利害關係人並不直接涉及企業主要營運與管理，若能提前預測企業財務危機，對於其投資決策則有重大的幫助。
早期財務危機預警分析較多以傳統統計方法做為分析工具，近年開始有學者從類神經網路工具來進行分析研究，然而隨著硬體設備的提升及多元的演算法，因此企業預警分析研究可以更加多元。本研究以台灣經濟新報資料庫為其樣本資料來源並以財務比率作為其自變數及搭配機器學習演算法來建立其財務預警預測模型，如決策樹、隨機森林、自身適應增強分類演算法、人工神經網路、支援向量機、K-近鄰演算法、羅吉斯迴歸、單純貝氏分類器等機器學習工具。本研究結果隨機森林明顯優於其他分類器，其AUC各別為0.850，是屬於Hosmer and Lemeshow (2000) 提到excellent discrimination.
關鍵詞：機器學習、財務危機預警、永續 | zh_TW |
| dc.description.abstract | Going concern basis is one of the assumptions when a company prepares financial reports. They have multiple challenges at a time, often across different categories today. Under the impacts of financial crisis in 2008 and the Coronavirus (COVID-19) in 2020, there were more operation risks on corporate failure or bankruptcies. If it can be predicted on finical crisis in advance, it is helpful on making investment decision for the investor and interested parties, because they are not involved in corporate operation.
People used the statical analysis on financial crisis precaution over the past year and they also used artificial neural network on their research. The advancement in Science and Technology Research provides us various way on financial crisis precaution research. The sample of this study uses the Taiwan Economic Journal Database. We also use the finical rates and non-financial rates with machine learning algorithms on building financial crisis precaution models, including Decision Tree, Random Forest, Adaptive Boosting, AdaBoost, Artificial Neural Network, SVM, K Nearest Neighbor, Logistic Regression, Navie Bayes. Random Forest is considered excellent discrimination of algorithm model on financial crisis precaution. The AUC results is 0.850 and this is between 0.8 and 0.9 is considered excellent discrimination by Hosmer and Lemeshow (2000).
Keywords: Machine Learning, Financial Crisis Precaution, and Sustainability. | en_US |
| DC.subject | 機器學習 | zh_TW |
| DC.subject | 財務危機預警 | zh_TW |
| DC.subject | 永續 | zh_TW |
| DC.subject | Machine Learning | en_US |
| DC.subject | Financial Crisis Precaution | en_US |
| DC.subject | Sustainability | en_US |
| DC.title | 以機器學習方法建構財務危機之預測模型：以台灣上市櫃公司為例 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Financial Crisis Precaution Model with Machine Leaning: Evidence from Taiwan Listed Company | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |