臺灣博碩士論文加值系統

近幾年舞弊案件接二連三地爆發，根據「2020 年全球經濟犯罪調查報告」中
顯示，財務報表舞弊兩年內提高 8%，排名從第七位上升至第五位。本研究旨在
運用機器學習技術建構出一套財務報表舞弊偵測系統，輔助查核人員在企業發生
舞弊之前能發現不尋常跡象，做出相對應的查核策略，重新擬定查核程式及流程，
進而將人力及資源投入在高風險之公司，增加查核深度以及查核效率與效果，並
增加查核報告之可靠性。本研究將以重抽樣技術處理不平衡資料集，研究結果顯
示，透過結合 SMOTE 重抽樣技術與 XGBoost 演算法可以建立最佳模型，而舞
弊前兩年度之資料、財務及公司治理變數之組合，皆有助於提高模型之分類能力。
最後本研究以隨機森林與 XGBoost 特徵重要性計算出每個特徵對於模型預測性
能的貢獻程度，排名前五的共同特徵為現金流量比率與獨立董監席次。

In recent years, fraud cases have broken out one after another. According to the
"2020 Global Economic Crime Survey Report", financial statement fraud has increased
by 8% within two years, rising from seventh to fifth. This research aims to leverage
machine learning technology to construct a financial statement fraud detection system,
which helps auditors detect unusual signs before fraud occurs in companies to make
corresponding audit strategies and redraw audit procedures and processes. As a result,
the workforce and resources can be invested in high-risk companies to increase the
depth, efficiency, and effectiveness of auditing to improve the reliability of audit
reports. This study used resampling technology to process imbalanced data sets. The
results show that the optimum model can be established by combining SMOTE
resampling technology and the XGBoost algorithm. In addition, the combination of
data two years before the fraud and financial and corporate governance variables can
help to improve the classification ability of the model. Finally, this study used the
random forest and XGBoost feature importance to calculate the contribution of each
feature to the prediction performance. The top five common features are the cash flow
ratio and the number of independent directors and supervisors.

摘要 I
Abstract II
謝辭 III
目錄 IV
表目錄 VI
圖目錄 VII
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 4
第三節 研究架構 6
第二章 文獻探討 7
第一節 財務報表舞弊之定義 7
第二節 辨認及評估舞弊風險因子 10
第三節 財務報表舞弊警示 14
一、財務性指標 14
二、公司治理指標 15
第四節 資料探勘應用於偵測財務報表舞弊相關文獻 16
第三章 研究設計 20
第一節 機器學習方式與建構模型步驟 20
一、機器學習方式 20
二、建構模型步驟 21
第二節 樣本選取與資料蒐集 23
一、舞弊公司之選取 23
二、正常公司之選取 24
第三節 研究變數 25
第四節 研究方法 29
一、分類模型之選用 29
二、處理不平衡資料集方法 31
三、模型評估指標 32
四、特徵重要性 36
第五節 研究流程設計 37
一、 以原始資料為基礎建構模型 37
二、以低額抽樣為基礎建構模型 38
三、以過額抽樣為基礎建構模型 38
第四章 研究結果與分析 40
第一節 樣本配對 40
第二節 模型結果與分析 42
一、各模式下之模型結果 42
二、模型比較 51
三、資料分布 52
四、加入舞弊前二年資料測試 53
五、特徵重要性 54
第五章 研究結論與建議 60
第一節 研究結論 60
第二節 研究建議 61
參考文獻 62

王毓軒，2011，〈使用資料探勘與公司治理變數建構舞弊預警模型〉，國立中正大學會計與資訊科技研究所碩士論文。
邢春玉、張莉，2020，〈大數據技術下的新審計模式研究〉，《財政監督》。
吳勇、何長添、方君、張超，2021，〈基於大數據挖掘分析的財務報表舞弊審計〉。
林嬋娟、廖珮真、盧信銘，2019，〈審計部 107-109 年度擁抱數位化風險與機會:運用資料探勘開創審計價值與影響〉，頁 26-29。
徐立群，2020，〈機器學習稽核-CRISP-DM 架構〉，《電腦稽核》，41 期，頁 58-65。
翁慈宗，2009，〈資料探勘的發展與挑戰〉，《專題報導資訊與生活科技》，頁 442。
陳雪如、黃劭彥、史雅男、蕭鎮臺，〈再探財務報表舞弊-風險因子新鑑識〉。
許伯彥，2003，〈財務報表舞弊風險評量模式硏究〉，國立臺灣大學會計學研究所碩士論文。
張漢傑，2014，〈第一上市公司(F 股)安全嗎？－以財務和非財務資訊分析解密〉，《會計研究月刊》，344 期，頁 75-85。
張文瀞、陳瑞斌、薛明賢，2019，〈長任期董事會的審計人員選擇〉，《管理學報》36(3)，頁 279-311。
張莉，2019，〈雲時代的舞弊審計――基於國家治理的新策略〉，Business & Economics，崧燁文化出版。
黄世忠、葉欽華、徐珊，2019，〈上市公司財務舞弊特徵分析〉，《財務與會計》，10-24 頁。
葉盈池 ，2018，〈大數據之運用與審計〉，《政府審計季刊》，頁38-46。
劉若蘭、李旻育，2017，〈董事會政治關聯, 客戶重要性對財務報導舞弊之影響〉。
劉若蘭、劉政淮、簡溥銘，2015，〈董監事暨重要職員責任保險與資訊揭露品質及企業舞弊關係之研究〉，《中華會計學刊》，11(1)，頁79-114。
劉桂良、葉寶松、周蘭，2009，〈舞弊治理:基於上市公司財務舞弊特徵的分析〉，《財經理論與實踐》，頁 52-56。
蘇柏翰，2016，〈運用資料探勘技術偵測財務報表舞弊―以台灣上市(櫃)公司為例〉，國立成功大學會計學研究所碩士論文。
Abarbanell, J. S., and B. J. Bushee. 1997. Fundamental analysis, future arnings, and stock prices. Journal of Accounting research 35 (1):1-24.
Abbott, L. J., S. Parker, and G. F. Peters. 2004. Audit committee haracteristics and restatements. Auditing: A journal of practice & theory 23 (1):69-87.
Aboud, A., and B. Robinson. 2020. Fraudulent financial reporting and data analytics: an explanatory study from Ireland. Accounting Research Journal.
Achakzai, M. A. K., and P. Juan. 2022. Using machine learning Meta-Classifiers to detect financial frauds. Finance Research Letters 48:102915.
Adam, T., and V. K. Goyal. 2008. The investment opportunity set and its proxy variables. Journal of Financial Research 31 (1):41-63.
Agrawal, R., and R. Srikant. 1994. Fast algorithms for mining association rules. Paper read at Proc. 20th int. conf. very large data bases, VLDB.
Ahmed, A. S., and I. Safdar. 2018. Dissecting stock price momentum using financial statement analysis. Accounting & Finance 58:3-43.
Altman, E. I. 1968. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance 23 (4):589-609.
Bai, B., J. Yen, and X. Yang. 2008. False financial statements: characteristics of China's listed companies and CART detecting approach. International journal of information technology & decision making 7 (2):339-359.
Ball, R., and L. Shivakumar. 2005. Earnings quality in UK private firms: comparative loss recognition timeliness. Journal of accounting and economics 39 (1):83-128.
Banz, R. W. 1981. The relationship between return and market value of common stocks. Journal of Financial Economics 9 (1):3-18.
Bao, Y., B. Ke, B. Li, Y. J. Yu, and J. Zhang. 2020. Detecting accounting fraud in publicly traded US firms using a machine learning approach. Journal of Accounting research 58 (1):199-235.
Basu, S. 1983. The relationship between earnings' yield, market value and return for NYSE common stocks: Further evidence. Journal of Financial Economics 12 (1):129-156.
Basu, S. 1997. The conservatism principle and the asymmetric timeliness of earnings1. Journal of accounting and economics 24 (1):3-37.
Beasley, M. S. 1996. An empirical analysis of the relation between the board of director composition and financial statement fraud. Accounting Review:443-465.
Beaver, W. H., and S. G. Ryan. 2000. Biases and lags in book value and their effects on the ability of the book-to-market ratio to predict book return on equity. Journal of Accounting research 38 (1):127-148.
———. 2005. Conditional and unconditional conservatism: Concepts and modeling. Review of accounting studies 10 (2):269-309.
Berry, M., and G. Linoff. 1997. Data mining techniques: For marketing, sales and marketing support. John Willey & Sons.
Bertomeu, J., E. Cheynel, E. Floyd, and W. Pan. 2021. Using machine learning to detect misstatements. Review of accounting studies 26 (2):468-519.
Beyer, B. D., D. R. Herrmann, and E. T. Rapley. 2019. Disaggregated capital expenditures. Accounting Horizons 33 (4):77-93.
Bonner, S. E., Z.-V. Palmrose, and S. M. Young. 1998. Fraud type and auditor litigation: An analysis of SEC accounting and auditing enforcement releases. Accounting Review:503-532.
Boulter, T., A. Mukherjee, and S. Bhattacharya. 2013. Motivation for occupational fraud: An analysis of the'fraud triangle'using economic logic. International journal of interdisciplinary organizational studies 7:47-59.
Breiman, L. 2001. Random forests. Machine learning 45 (1):5-32.
Cecchini, M., H. Aytug, G. J. Koehler, and P. Pathak. 2010. Detecting management fraud in public companies. Management Science 56 (7):1146-1160.
Chawla, N. V., K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. 2002. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research 16:321-357.
Chen, G., M. Firth, D. N. Gao, and O. M. Rui. 2006. Ownership structure, corporate governance, and fraud: Evidence from China. Journal of corporate finance 12 (3):424-448.
Chen, H.-Y., C. F. Lee, and W.-K. Shih. 2016. Technical, fundamental, and combined information for separating winners from losers. In HANDBOOK OF FINANCIAL ECONOMETRICS, MATHEMATICS, STATISTICS, AND MACHINE LEARNING: World Scientific, 3319-3365.
Chen, L. H., D. M. Folsom, W. Paek, and H. Sami. 2014a. Accounting conservatism, earnings persistence, and pricing multiples on earnings. Accounting Horizons 28 (2):233-260.
Chen, S. 2016. Detection of fraudulent financial statements using the hybrid data mining approach. SpringerPlus 5 (1):1-16.
Chen, S., Y.-J. J. Goo, and Z.-D. Shen. 2014b. A hybrid approach of stepwise regression, logistic regression, support vector machine, and decision tree for forecasting fraudulent financial statements. The Scientific World Journal 2014.
Chen, T., and C. Guestrin. 2016. Xgboost: A scalable tree boosting system. Paper read at Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.
Chen, Y.-J., W.-C. Liou, Y.-M. Chen, and J.-H. Wu. 2019. Fraud detection for financial statements of business groups. International Journal of Accounting Information Systems 32:1-23.
Cheng, C.-H., Y.-F. Kao, and H.-P. Lin. 2021. A financial statement fraud model based on synthesized attribute selection and a dataset with missing values and imbalanced classes. Applied Soft Computing 108:107487.
Cortes, C., and V. Vapnik. 1995. Support-vector networks. Machine learning 20 (3):273-297.
Craja, P., A. Kim, and S. Lessmann. 2020. Deep learning for detecting financial statement fraud. Decision support systems 139:113421.
Daniel, K., M. Grinblatt, S. Titman, and R. Wermers. 1997. Measuring mutual fund performance with characteristic‐based benchmarks. The Journal of Finance 52 (3):1035-1058.
Danielson, M. G., and T. D. Dowdell. 2001. The return-stages valuation model and the expectations within a firm's P/B and P/E ratios. Financial Management:93-124.
Dechow, P. M., W. Ge, C. R. Larson, and R. G. Sloan. 2011. Predicting material accounting misstatements. Contemporary Accounting Research 28 (1):17-82.
Dietrich, J. R., K. A. Muller, and E. J. Riedl. 2007. Asymmetric timeliness tests of accounting conservatism. Review of accounting studies 12 (1):95-124.
Dorminey, J., A. S. Fleming, M.-J. Kranacher, and R. A. Riley Jr. 2012. The evolution of fraud theory. Issues in accounting education 27 (2):555-579.
Dyck, A., A. Morse, and L. Zingales. 2010. Who blows the whistle on corporate fraud? The Journal of Finance 65 (6):2213-2253.
Elkan, C. 2001. Magical thinking in data mining: lessons from CoIL challenge 2000. Paper read at Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining.
Fama, E. F., and K. R. French. 1993. Common risk factors in the returns on stocks and bonds. Journal of Financial Economics 33:3-56.
Fanning, K. M., and K. O. Cogger. 1998. Neural network detection of management fraud using published financial data. Intelligent Systems in Accounting, Finance
& Management 7 (1):21-41.
Gepp, A., K. Kumar, and S. Bhattacharya. 2021. Lifting the numbers game: identifying key input variables and a best‐performing model to detect financial statement fraud. Accounting & Finance 61 (3):4601-4638.
Gepp, A. C. 2015. Financial statement fraud detection using supervised learning methods: Bond University Gold Coast.
Gerety, M., and K. Lehn. 1997. The causes and consequences of accounting fraud. Managerial and Decision Economics 18 (7‐8):587-599.
Givoly, D., and C. Hayn. 2000. The changing time-series properties of earnings, cash flows and accruals: Has financial reporting become more conservative? Journal of accounting and economics 29 (3):287-320.
Givoly, D., C. K. Hayn, and A. Natarajan. 2007. Measuring reporting conservatism. The Accounting Review 82 (1):65-106.
Green, B. P., and J. H. Choi. 1997. Assessing the risk of management fraud through neural network technology. Auditing 16:14-28.
Gupta, R., and N. S. Gill. 2012. Prevention and detection of financial statement fraud–An implementation of data mining framework. International Journal of Advanced Computer Science and Applications 3 (8).
Huberts, L. C., and R. J. Fuller. 1995. Predictability bias in the US equity market. Financial Analysts Journal 51 (2):12-28.
Jegadeesh, N., and S. Titman. 1993. Returns to buying winners and selling losers: Implications for stock market efficiency. The Journal of Finance 48 (1):65-91.
Jensen, M. C. 1993. The modern industrial revolution, exit, and the failure of internal control systems. The Journal of Finance 48 (3):831-880.
Jofre, M., and R. Gerlach. 2018. Fighting accounting fraud through forensic data analytics. arXiv preprint arXiv:1805.02840.
Juszczak, P., N. M. Adams, D. J. Hand, C. Whitrow, and D. J. Weston. 2008. Off-the-peg and bespoke classifiers for fraud detection. Computational Statistics & Data Analysis 52 (9):4521-4532.
Kantardzic, M. 2011. Data mining: concepts, models, methods, and algorithms: John Wiley & Sons.
Khan, M., and R. L. Watts. 2009. Estimation and empirical properties of a firm-year measure of accounting conservatism. Journal of accounting and economics 48 (2-3):132-150.
Khedr, A. M., M. El Bannany, and S. Kanakkayil. 2021. An Ensemble Model for Financial Statement Fraud Detection. ARPHA Preprints 2:e69590.
Kim, Y. J., B. Baik, and S. Cho. 2016. Detecting financial misstatements with fraud intention using multi-class cost-sensitive learning. Expert systems with applications 62:32-43.
Kirkos, E., C. Spathis, and Y. Manolopoulos. 2007. Data mining techniques for the detection of fraudulent financial statements. Expert systems with applications 32 (4):995-1003.
Koh, H. C., and C. K. Low. 2004. Going concern prediction using data mining techniques. Managerial Auditing Journal 19 (3):462-476.
Koskivaara, E. 2003. Artificial neural networks in auditing: state of the art: Citeseer.
La Porta, R., F. Lopez‐de‐Silanes, and A. Shleifer. 1999. Corporate ownership around the world. The Journal of Finance 54 (2):471-517.
Lakonishok, J., A. Shleifer, and R. W. Vishny. 1994. Contrarian investment, extrapolation, and risk. The Journal of Finance 49 (5):1541-1578.
Lara, J. M. G., B. G. Osma, and F. Penalva. 2009. Accounting conservatism and corporate governance. Review of accounting studies 14 (1):161-201.
Larose, D. T., and C. Larose. 2005. Discovering Knowledge in Data: John Willey And Sons. Inc., Publication, New Jersey.
Lessmann, S., B. Baesens, H.-V. Seow, and L. C. Thomas. 2015. Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research 247 (1):124-136.
Lev, B., and S. R. Thiagarajan. 1993. Fundamental information analysis. Journal of Accounting research 31 (2):190-215.
Lin, C.-C., A.-A. Chiu, S. Y. Huang, and D. C. Yen. 2015. Detecting the financial statement fraud: The analysis of the differences between data mining techniques and experts’ judgments. Knowledge-Based Systems 89:459-470.
Lintner, J. 1965. THE VALUATION OF RISK ASSETS AND THE SELECTION OF RISKY INVESTMENTS IN STOCK PORTFOLIOS AND CAPITAL BUDGETS. The Review of Economics and Statistics 47 (1):13-37.
Liu, C., Y. Chan, S. H. Alam Kazmi, and H. Fu. 2015. Financial fraud detection model: Based on random forest. International journal of economics and finance 7 (7).
Liu, Z., R. Ye, and R. Ye. 2021. Detecting Financial Statement Fraud with Interpretable Machine Learning.
Lou, Y.-I., and M.-L. Wang. 2009. Fraud risk factor of the fraud triangle assessing the likelihood of fraudulent financial reporting. Journal of Business & Economics Research (JBER) 7 (2).
Markelevich, A., and R. L. Rosner. 2013. Auditor fees and fraud firms. Contemporary Accounting Research 30 (4):1590-1625.
McKee, T. E. 2009. A meta-learning approach to predicting financial statement fraud. Journal of Emerging Technologies in Accounting 6 (1):5-26.
Mohanram, P. S. 2005. Separating winners from losers among lowbook-to-market stocks using financial statement analysis. Review of accounting studies 10 (2-3):133-170.
Mokhiber, R., and R. Weissman. 2005. The 10 worst corporations of 2005. Multinational Monitor 26 (11/12):10.
Myers, S. C., and N. S. Majluf. 1984. Corporate financing and investment decisions when firms have information that investors do not have. Journal of Financial Economics 13 (2):187-221.
Ngai, E. W., Y. Hu, Y. H. Wong, Y. Chen, and X. Sun. 2011. The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature. Decision support systems 50 (3):559-569.
Noma, M. 2010. Value investing and financial statement analysis. Hitotsubashi journal of commerce and management:29-46.
Omoye, A. S., and E. Eragbhe. 2014. Accounting ratios and false financial statements detection: evidence from Nigerian quoted companies. International Journal of Business and Social Science 5 (7):206-215.
Ou, J. A., and S. H. Penman. 1989. Financial statement analysis and the prediction of stock returns. Journal of accounting and economics 11 (4):295-329.
Pae, J., D. B. Thornton, and M. Welker. 2005. The link between earnings conservatism and the price‐to‐book ratio. Contemporary Accounting Research 22 (3):693-717.
Pai, P.-F., M.-F. Hsu, and M.-C. Wang. 2011. A support vector machine-based model for detecting top management fraud. Knowledge-Based Systems 24 (2):314-321.
Perfect, S. B., and K. W. Wiles. 1994. Alternative constructions of Tobin's q: An empirical comparison. Journal of empirical finance 1 (3-4):313-341.
Perols, J. 2011. Financial statement fraud detection: An analysis of statistical and machine learning algorithms. Auditing: A journal of practice & theory 30 (2):19-50.
Perols, J. L., R. M. Bowen, C. Zimmermann, and B. Samba. 2017. Finding needles in a haystack: Using data analytics to improve fraud prediction. The Accounting Review 92 (2):221-245.
Perols, J. L., and B. A. Lougee. 2011. The relation between earnings management and financial statement fraud. Advances in Accounting 27 (1):39-53.
Persons, O. S. 1995. Using financial statement data to identify factors associated with fraudulent financial reporting. Journal of Applied Business Research (JABR) 11 (3):38-46.
Pástor, Ľ., and V. Pietro. 2003. Stock valuation and learning about profitability. The Journal of Finance 58 (5):1749-1789.
Ravisankar, P., V. Ravi, G. R. Rao, and I. Bose. 2011. Detection of financial statement fraud and feature selection using data mining techniques. Decision support systems 50 (2):491-500.
Rezaee, Z. 2002. Financial statement fraud: prevention and detection: John Wiley & Sons.
Romney, M., P. Steinbart, J. Mula, R. McNamara, and T. Tonkin. 2012. Accounting Information Systems Australasian Edition: Pearson Higher Education AU.
Rosenberg, B., K. Reid, and R. Lanstein. 1985. Persuasive evidence of market inefficiency. The Journal of Portfolio Management 11 (3):9-16.
Roychowdhury, S., and R. L. Watts. 2007. Asymmetric timeliness of earnings, market-to-book and conservatism in financial reporting. Journal of accounting and economics 44 (1-2):2-31.
Schilit, H. 2010. Financial shenanigans: Tata McGraw-Hill Education.
Sharda, R., D. Delen, E. Turban, J. Aronson, and T. Liang. 2014. Business intelligence and analytics. System for Decesion Support.
Sharma, M., and Preeti. 2009. Prediction of stock returns for growth firms—A fundamental analysis. Vision 13 (3):31-40.
Sharma, V. D. 2004. Board of director characteristics, institutional ownership, and fraud: Evidence from Australia. Auditing: A journal of practice & theory 23 (2):105-117.
Sharpe, W. F. 1964. Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance 19 (3):425-442.
Sikalidis, A. 2021. Corporate Governance, CEO Compensation and accounting conservatism. International Journal of Business and Economic Sciences Applied
Research (IJBESAR) 14 (1):80-95.
Skousen, C. J., K. R. Smith, and C. J. Wright. 2009. Detecting and predicting financial statement fraud: The effectiveness of the fraud triangle and SAS No. 99. In Corporate governance and firm performance: Emerald Group Publishing Limited.
Smith Jr, C. W., and R. L. Watts. 1992. The investment opportunity set and corporate financing, dividend, and compensation policies. Journal of Financial Economics 32 (3):263-292.
Sofaer, H. R., J. A. Hoeting, and C. S. Jarnevich. 2019. The area under the precision‐recall curve as a performance metric for rare binary events. Methods in Ecology and Evolution 10 (4):565-577.
Song, X. P., Z. H. Hu, J. G. Du, and Z. H. Sheng. 2014. Application of machine learning methods to risk assessment of financial statement fraud: evidence from China. Journal of Forecasting 33 (8):611-626.
Summers, S. L., and J. T. Sweeney. 1998. Fraudulently misstated financial statements and insider trading: An empirical analysis. Accounting Review:131-146.
Van Vugt, M., R. Hogan, and R. B. Kaiser. 2008. Leadership, followership, and evolution: some lessons from the past. American Psychologist 63 (3):182.
Wang, R., V. Asghari, S.-C. Hsu, C.-J. Lee, and J.-H. Chen. 2020. Detecting corporate misconduct through random forest in China’s construction industry. Journal of cleaner production 268:122266.
Yeh, I.-C., and T.-K. Hsu. 2011. Growth value two-factor model. Journal of Asset Management 11 (6):435-451.
Zainudin, E. F., and H. A. Hashim. 2016. Detecting fraudulent financial reporting using financial ratio. Journal of Financial Reporting and Accounting.
Zhou, W., and G. Kapoor. 2011. Detecting evolutionary financial statement fraud. Decision support systems 50 (3):570-575.