跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 烏堤卡
Richa Etika Ulhaq
論文名稱： 三年看門狗事件在危機預測已台灣上市上櫃公司為例
Three-Year Periods Watchdog Events for Predicting Crisis Phase Using Taiwan Listed Companies Dataset
指導教授： 梁德容
Deron Liang
盧佳琪
Lu Nina
口試委員:
學位類別： 碩士
Master
系所名稱： 資訊電機學院 - 資訊工程學系
Department of Computer Science & Information Engineering
論文出版年： 2019
畢業學年度： 107
語文別： 英文
論文頁數： 73
中文關鍵詞： 看門狗事件 、財務比率 、危機預測
外文關鍵詞： watchdog events, financial ratio, crisis prediction
相關次數： 點閱：17  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 許多研究著重於通過使用財務比率或將其與公司治理指標相結合來預測破產，而本研究追求的是使用公司負面新聞事件來預測公司的第一次危機，而這個危機會對公司帶來實際上的損害，這可能是防止他們破產的第一步。 在看門狗資料庫中所記錄每家上市上櫃公司的事件資訊，可用於預測公司的財務危機。 本研究採用統計學和機器學習方法用危機前三年的事件作為特徵來預測公司發生的第一次危機，此方法受研究問題的推動：實驗所選擇的自三年前開始的看門狗事件是否有助於提高預測第一次的危機表現？ 為了瞭解這個問題，我們提出了一個模型是通過財務比率和看門狗事件中的五種事件的組合所建立的。

    While many studies focused on predicting bankruptcy by using financial ratios or combining them with corporate governance indicators, this study pursue a crisis events which causes lose to a company to predict their first crisis which can be an initial step to prevent them to be bankrupt in the future. Recorded events information-gathered by watchdog dataset of Taiwan listed companies-before the financial crisis happened in a company can be used to predict financial crisis in a company. This study focus on the prediction start from three year periods before first crisis happened in a company using statistical and machine learning method which is motivated with the research question: could the chosen watchdog events help to improve the performance of crisis prediction start from three years before first crisis? To acknowledge this question, a proposed model is built by a combination of financial ratios and five events gathered by watchdog using Taiwan listed companies.

    Table of Contents ABSTRACT i 摘 要 ii ACKNOWLEDGEMENTS iii 1 Introduction 1 1.1 Background 1 1.2 Problem Statements 2 1.3 Outline of Chapters 2 1.4 Research Limitations 2 2 Literature Review 3 2.1 Previous Work 3 2.2 Financial Ratio 4 2.3 Watchdog Events 4 2.4 T-Test for Statistical Tests of Significance 6 2.5 Ensemble Methods 7 2.5.1 Bagging 8 2.5.2 Random Forest 8 2.6 Support Vector Machine 9 2.7 K-Nearest Neighbors 10 3 Research Method 11 3.1 Experiment Architecture 11 3.2 Dataset 12 3.3 Data Pre-processing 12 3.3.1 Defining Crisis Company 13 3.3.2 Matching Method 15 3.3.3 Feature Selection Method 16 3.4 Experiment Design 19 3.5 Model Building 20 3.6 Evaluation Metrics 22 3.7 Result Overview 22 3.7.1 DET Curve 23 3.7.2 Wilcoxon Test 24 3.8 Experiment Settings 25 4 Experiment Results 26 4.1 Experiment Result of T-3 27 4.1.1 Baseline Model T-3 27 4.1.2 Proposed Model T-3 28 4.1.3 Proposed vs Baseline Model T-3 29 4.2 Experiment Result of T-2 31 4.2.1 Baseline Model T-2 31 4.2.2 Proposed Model T-2 32 4.2.3 Baseline vs Proposed Model T-2 33 4.3 Experiment Result of T-1 35 4.3.1 Baseline Model T-1 36 4.3.2 Proposed Model T-1 37 4.3.3 Proposed vs Baseline Model T-1 38 5 Conclusion and Suggestion 40 5.1 Conclusion 40 5.2 Suggestion 40 BIBLIOGRAPHY 41 Appendixes A 42 Appendixes B 48 Appendixes C 51 Appendixes D 54

    BIBLIOGRAPHY
    [1] D. Katayama and K. Tsuda. 2018. A Method of Measurement of the Impact of Japanese News on Stock Market. Procedia Computer Science 126, 1336–1343.
    [2] D. Liang, C.-C. Lu, C.-F. Tsai, and G.-A. Shih. 2016. Financial Ratios and Corporate Governance Indicators in Bankruptcy Prediction: A Comprehensive Study. European Journal of Operational Research, Vol. 252, No. 2, pp. 561-572.
    [3] F. Lin, D. Liang, and W-S. Chu. 2010. The Role of Non-Financial Features Related to Corporate Governance in Business Crisis Prediction. Journal of Marine Science and Technology, Vol. 18, No. 4, pp. 504-513.
    [4] G.D. Ruxtom. 2006. The Unequal Variance t-test is an Underused alternative to Student’s t-test and the mann-Whitney U test. Behavioral Ecology.
    [5] I.E. Altman.1968. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, vol. 23, no. 4, pp. 589-609.
    [6] J. Han, M. Kamber, and J. Pei. 2012. Third Edition: Data Mining; Concept and Technique. Morgan Kauffman Publisher of Elsivier, USA.
    [7] M. Anandarajan, P. Lee, and A. Anandarajan. 2001. Bankruptcy Prediction of Financial Stressed Firms: An Examination of the Predictive Accuracy of Artificial Neural Networks. Int. J. Intell. Sys. Acc. Fin. Mgmt. 10, 69–81.
    [8] P.D. Jardin, D. Veganzones. 2017. Forecasting Corporate Bankruptcy Using Accrual-Based Models. Springer Science+Business Media New York.
    [9] P. Slovic. 1972. Psychological Study of Human Judgment: Implication for Investment Decision Making. The Journal of Finance.
    [10] W. H, Beaver. 1966. Financial Ratios as Predictors Failure. Journal of Accounting Research, Vol. 4, Empirical Research in Accounting: Selected Studies 1966.

    QR CODE
    :::