跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/23 13:54
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:馮少辰
研究生(外文):FENG, SHAO-CHEN
論文名稱:以機器學習方式辨認財務危機公司 -納入重大訊息之考量
論文名稱(外文):Identifying Financial Distress Companies by Machine Learning: Under the Considerations of Material Information
指導教授:高立翰高立翰引用關係
指導教授(外文):KAO, LI-HAN
口試委員:高立翰沈大白顏如君
口試委員(外文):KAO, LI-HANSHEN, DA-BAIYEN, JU-CHUN
口試日期:2022-06-15
學位類別:碩士
校院名稱:東吳大學
系所名稱:會計學系
學門:商業及管理學門
學類:會計學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:49
中文關鍵詞:財務危機重大訊息機器學習文字探勘
外文關鍵詞:Financial DistressMaterial InformationMachine LearningText Mining
相關次數:
  • 被引用被引用:1
  • 點閱點閱:101
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
過去研究所建立的財務危機預測模型大抵分為兩類,一為利用財務指標從公司的財務面找出公司破產的徵兆,二為加入非財務方面資訊,如公司治理相關指標,結合財務面以加強對於公司財務危機預測的準確率。近期受惠於網路發達,大量數位化文字資料的產生,也提高了文字資訊對於判斷財務危機時的重要性及影響。有鑑於此,本研究欲以公開資訊觀測站中之重大訊息納入財務危機預測模型,以提供不同利害關係人更多面向的考量。實證結果顯示,當公司發布重大訊息含有特定關鍵詞,且其中負面詞彙出現頻率越高,則公司越容易存有財務危機。而重大訊息中之中性詞彙則可以作為排除與財務危機無關之訊息之參考,以縮小存有可能產生財務危機訊息的範圍。最後,本研究使用共四種機器學習方法來訓練並驗證納入重大訊息關鍵詞後之財務危機預警模型準確度。辨認方法準確率由高至低分別為隨機森林73.35%、羅吉斯迴歸65.96%、支援向量機63.72及K-近鄰演算法55.15,最終結果可得到隨機森林法為最佳預測模型。
The financial distress prediction models developed by the previous s were generally divided into two categories, one is to use financial indicators to identify the signs of company bankruptcy from the financial side of the company, and the other is to add non-financial information. Such non-financial factors including corporate governance-related indicators are usually combined with financial aspects to enhance the accuracy of the prediction of company financial distress. As a result of recent internet development and the generation of huge digital textual information, the textual information has also increased its importance and impact on determining financial crises. Under the circumstances, this study focuses on incorporating material information retrieved from the Public Information Observation Post System (PIO) into the financial distress prediction model to provide a multi-orientation evaluation for different stakeholders. The empirical results show that companies are more likely to face financial crises when they release major messages containing specific keywords and more negative words. Besides, the neutral terms in major messages can be used as a reference to exclude messages that are not related to financial crises to narrow the scope of messages that may generate financial crises. Finally, four machine learning methods are used to train and validate the accuracy of the financial crisis prediction model after incorporating keywords in the critical messages. The accuracy rates of the four methods were 73.35% for Random Forest, 65.96% for Logistic Regression, 63.72% for Support Vector Machine, and 55.15% for K-Nearest Neighbor algorithm. The final results showed that Random Forest was the best prediction model for financial distress.
摘要 I
Abstract II
目錄 III
表目錄 V
圖目錄 VI
第一章 緒論 1
第一節 研究背景及動機 1
第二節 論文架構 4
第二章 文獻回顧 5
第一節 財務危機 5
一、財務危機定義 5
二、財務危機相關研究 7
第二節 資訊揭露與相關管道 9
一、資訊揭露與透明度 9
二、公開資訊觀測站之發展沿革與相關法令 10
三、國外資訊揭露方式與規範 13
第三節 資料探勘與機器學習 17
一、資料探勘定義與應用 17
二、機器學習定義、分析模式及相關文獻探討 17
三、文字探勘定義及相關文獻探討 18
第三章 研究方法與設計 20
第一節 研究樣本與流程設計 20
第二節 文字探勘方法介紹 21
第三節 變數定義及迴歸驗證模型 21
第四節 機器學習方法介紹 23
一、羅吉斯迴歸(Logistic Regression) 23
二、隨機森林(Random Forest) 24
三、支援向量機(Support Vector Machine, SVM) 24
四、K-近鄰演算法(K-Nearest Neighbor, K-NN) 25
第四章 實證結果 26
第一節 敘述性統計 26
第二節 羅吉斯迴歸 31
一、模型選定 31
二、假說1實證結果與分析 33
三、假說2、假說3實證結果與分析 36
四、小結 40
第三節 以機器學習方式建立預測模型 40
第五章 結果與建議 43
第一節 結論 43
第二節 研究貢獻 44
第三節 研究限制 44
第四節 未來研究建議 45
參考文獻 46

余惠芳、潘麗卿,2014,〈以勝算比觀點分析企業營運策略、公司治理與財務預測-台灣上市櫃股之實證研究〉,《全球管理與經濟》,第10卷((2期):57-77頁。
Alfiah, N., and L. A. Diyani. 2017. Pengaruh ROE dan DER terhadap Harga Saham Pada Sektor Perdagangan Eceran. Jurnal Bisnis Terapan 1 (02):47-54.
Altman, E. I. 1968. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance 23 (4):589-609.
Amir, E., T. S. Harris, and E. K. Venuti. 1993. A comparison of the value-relevance of US versus non-US GAAP accounting measures using form 20-F reconciliations. Journal of Accounting Research 31:230-264.
Andrade, G., and S. N. Kaplan. 1998. How costly is financial (not economic) distress? Evidence from highly leveraged transactions that became distressed. The Journal of Finance 53 (5):1443-1493.
Barboza, F., H. Kimura, and E. Altman. 2017. Machine learning models and bankruptcy prediction. Expert systems with applications 83:405-417.
Barkur, G., and G. B. K. Vibha. 2020. Sentiment analysis of nationwide lockdown due to COVID 19 outbreak: Evidence from India. Asian journal of psychiatry 51:102089.
Beaver, W. H. 1966. Financial ratios as predictors of failure. Journal of Accounting Research:71-111.
Beaver, W. H., M. F. McNichols, and J.-W. Rhie. 2005. Have financial statements become less informative? Evidence from the ability of financial ratios to predict bankruptcy. Review of Accounting studies 10 (1):93-122.
Bell, E., A. Bryman, and B. Harley. 2018. Business research methods: Oxford university press.
Black, B. S., H. Jang, and W. Kim. 2003. Does corporate governance affect firm value?: evidence from Korea.
Bloomfield, R. J., and T. J. Wilks. 2000. Disclosure effects in the laboratory: Liquidity, depth, and the cost of capital. The Accounting Review 75 (1):13-41.
Boser, B. E., I. M. Guyon, and V. N. Vapnik. 1992. A training algorithm for optimal margin classifiers. Paper read at Proceedings of the fifth annual workshop on Computational learning theory.
Breiman, L. 1996. Bagging predictors. Machine learning 24 (2):123-140.
Carton, R. B., and C. W. Hofer. 2006. Measuring organizational performance: Metrics for entrepreneurship and strategic management research: Edward Elgar Publishing.
Chen, H.-C., and C.-W. Yeh. 2021. Global financial crisis and COVID-19: Industrial reactions. Finance Research Letters:101940.
Coats, P. K., and L. F. Fant. 1993. Recognizing financial distress patterns using a neural network tool. Financial management:142-155.
Devikanniga, D., A. Ramu, and A. Haldorai. 2020. Efficient Diagnosis of Liver Disease using Support Vector Machine Optimized with Crows Search Algorithm. EAI Endorsed Transactions on Energy Web 7.
Diamond, D. W., and R. E. Verrecchia. 1991. Disclosure, liquidity, and the cost of capital. The Journal of Finance 46 (4):1325-1359.
Dunham, L. M., and J. Garcia. 2021. Measuring the effect of investor sentiment on financial distress. Managerial Finance.
Elagamy, M. N., C. Stanier, and B. Sharp. 2018. Stock market random forest-text mining system mining critical indicators of stock market movements. Paper read at 2018 2nd International Conference on Natural Language and Speech Processing (ICNLSP).
Gertner, R., and D. Scharfstein. 1991. A theory of workouts and the effects of reorganization law. The Journal of Finance 46 (4):1189-1222.
Healy, P. M., and K. G. Palepu. 1993. The effect of firms' financial disclosure strategies on stock prices. Accounting horizons 7 (1):1.
Healy, P. M., and J. M. Wahlen. 1999. A review of the earnings management literature and its implications for standard setting. Accounting horizons 13 (4):365-383.
Jabeur, S. B., and Y. Fahmi. 2018. Forecasting financial distress for French firms: a comparative study. Empirical Economics 54 (3):1173-1186.
Jordan, M. I., and T. M. Mitchell. 2015. Machine learning: Trends, perspectives, and prospects. Science 349 (6245):255-260.
Kristanti, F. T., and A. Herwany. 2017. Corporate governance, financial ratios, political risk and financial distress: A survival analysis. Accounting and Finance Review (AFR) Vol 2 (2).
Lau, A. H.-L. 1987. A five-state financial distress prediction model. Journal of Accounting Research:127-138.
Leftwich, R. 1980. Market failure fallacies and accounting information. Journal of Accounting and Economics 2 (3):193-211.
Loughran, T., and B. McDonald. 2011. When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. The Journal of Finance 66 (1):35-65.
Marso, S., and M. El Merouani. 2020. Predicting financial distress using hybrid feedforward neural network with cuckoo search algorithm. Procedia Computer Science 170:1134-1140.
Mashudi, M., R. Himmati, I. F. R. Ardillah, and C. Sarasmitha. 2021. Financial Distress Prediction in Infrastructure, Utilities, and Transportation Sector Companies 2015-2020. Jurnal Keuangan dan Perbankan 25 (3):656-670.
Mayew, W. J., and M. Venkatachalam. 2012. The power of voice: Managerial affective states and future firm performance. The Journal of Finance 67 (1):1-43.
Odom, M. D., and R. Sharda. 1990. A neural network model for bankruptcy prediction. Paper read at 1990 IJCNN International Joint Conference on neural networks.
Ohlson, J. A. 1980. Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research:109-131.
Patel, S. A., A. Balic, and L. Bwakira. 2002. Measuring transparency and disclosure at firm-level in emerging markets. Emerging markets review 3 (4):325-337.
Pervan, I., M. Pervan, and T. Kuvek. 2018. Firm Failure Prediction: Financial Distress Model vs Traditional Models. Croatian Operational Research Review:269-279.
Pranita, K. R., and F. T. Kristanti. 2020. Analisis Financial Distress Menggunakan Analisis Survival. Nominal: Barometer Riset Akuntansi dan Manajemen 9 (2):62-79.
Raffournier, B. 1995. The determinants of voluntary financial disclosure by Swiss listed companies. European accounting review 4 (2):261-280.
Shah, K., H. Patel, D. Sanghvi, and M. Shah. 2020. A comparative analysis of logistic regression, random forest and KNN models for the text classification. Augmented Human Research 5 (1):1-16.
Shumway, T. 2001. Forecasting bankruptcy more accurately: A simple hazard model. The journal of business 74 (1):101-124.
Singhvi, S. S., and H. B. Desai. 1971. An empirical analysis of the quality of corporate financial disclosure. The Accounting Review 46 (1):129-138.
Speiser, J. L., M. E. Miller, J. Tooze, and E. Ip. 2019. A comparison of random forest variable selection methods for classification prediction modeling. Expert systems with applications 134:93-101.
Tang, X., S. Li, M. Tan, and W. Shi. 2020. Incorporating textual and management factors into financial distress prediction: A comparative study of machine learning methods. Journal of Forecasting 39 (5):769-787.
Wang, G., G. Chen, and Y. Chu. 2018. A new random subspace method incorporating sentiment and textual information for financial distress prediction. Electronic Commerce Research and Applications 29:30-49.
Welker, M. 1995. Disclosure policy, information asymmetry, and liquidity in equity markets. Contemporary accounting research 11 (2):801-827.
Wilson, R. L., and R. Sharda. 1994. Bankruptcy prediction using neural networks. Decision support systems 11 (5):545-557.
Wruck, K. H. 1990. Financial distress, reorganization, and organizational efficiency. Journal of financial economics 27 (2):419-444.
Xu, G., Y. Meng, X. Qiu, Z. Yu, and X. Wu. 2019. Sentiment analysis of comment texts based on BiLSTM. IEEE access 7:51522-51532.
Yang, L., Y. Li, J. Wang, and R. S. Sherratt. 2020. Sentiment analysis for E-commerce product reviews in Chinese based on sentiment lexicon and deep learning. IEEE access 8:23522-23530.
Zmijewski, M. E. 1984. Methodological issues related to the estimation of financial distress prediction models. Journal of Accounting Research:59-82.


電子全文 電子全文(網際網路公開日期:20270705)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊