臺灣博碩士論文加值系統

近年來，多數上市公司紛紛無預警地爆發財務危機。對於大多數的投資人以及資金授信者而言，這些財務危機的發生幾乎是不可預知的，尤其當牽涉盈餘管理時更是如此。因為盈餘管理係管理階層透過特定方法或程序用以操縱會計盈餘進而達成一己之私利的過程，因此隱藏的財務危機更得以窗飾。
在盈餘管理的相關文獻中，已有多數研究指出何種因素對於盈餘管理有顯著影響。然而這些因素雖然與盈餘管理具有相關性，但是卻未被直接用來預測盈餘管理的程度。
為了減少盈餘管理所帶來的財務危機風險以及幫助投資人避免巨額的投資虧損，本研究開發出一套類神經網路模型用以預測盈餘管理。類神經網路技術已在釵h領域中被證實其在模型建立以及預測上具有極佳的效果。本研究主要目的在於探討類神經網路是否對於向上及向下盈餘操縱具備預測之能力。
本研究採用台灣經濟新報資料庫系統作為資料來源，並且根據文獻選取了11個與盈餘管理相關的輸入變數。本研究經過交叉驗證之後發現，類神經網路對於向上盈餘操縱的預測準確度最高可達81.08%。此外，本研究亦利用決策樹塑模方法建立CART以及C5.0二種決策樹模型，發現了有趣的預測向上盈餘管理的規則。也就是同時具備低公司績效、高盈餘持續性以及已發行股數變動量高者，其向上盈餘操縱的可能性極高。

Recently, one of the most attractive business news is a series of financial crisis cases related to the public companies. However, many investors and creditors cannot foresee the financial crisis, especially in the cases with earnings management. Earnings management is manipulating earnings in accounting to fulfill managers’ purposes using certain methods or processes.
In literature, many studies related to earnings management only focus on identifying some related factors which can significantly affect earnings management. That is, we can only figure out the correlation between these factors and earnings management. However, these factors have not been used directly to forecast the level of earnings management in advance.
In order to decrease the financial crisis risks derived from earnings management and help the investors avoid suffering a great loss in the stock market, we developed a neural network model to predict the level of earnings management. Neural networks have been proven to possess the most practical effect in modeling and forecasting in many areas. The aim of this paper is to investigate the applicability of neural networks for predicting upwards and downwards of earnings management.
We used the TEJ database and 11 input variables which are selected based on the related factors identified in literature. After running 5-fold cross-validation, the accuracy of the prediction model can reach up to 81.08% in the cases of manipulating earnings upwards. Besides, we also developed the decision trees models trained and tested by CART and C5.0. In the built decision trees, we found several rules to predict the upward earnings management cases. That is, upward earnings management will most likely occur in the firms which simultaneously have low firm performance, high earnings persistence and the outstanding shares increased or decreased by 10%.

LIST OF TABLES v
LIST OF FIGURES vi
Chapter 1 Introduction 1
1.1. Motivation 1
1.2. Aim and Objectives 4
1.2.1. Aim 4
1.2.2. Objectives 4
1.3. Contribution 5
1.4. Structure of the Thesis 7
Chapter 2 Literature Review 8
2.1. Earnings Management 8
2.1.1. Definition of Earnings Management 8
2.1.2. Related Work of Earnings Management 9
2.2. Measurement of Earnings Management 21
2.2.1. The Proxy of Earnings Management 21
2.2.2. Choice of Measuring Models 21
2.2.3. The Cross-Sectional Jones Model 23
2.3. Data Mining 25
2.3.1. Definition of Data Mining 25
2.3.2. Data Mining Strategies 26
2.4. Neural Networks 29
2.4.1. Definition and Architecture of Neural Networks 29
2.4.2. Backpropagation Algorithm 32
2.5. Discussion 35
Chapter 3 Experimental Methodology 37
3.1. Sample Selection and Data Collection 39
3.2. Variables Selection 40
3.2.1. Related Variables 40
3.2.2. An Example For Variables Selection 46
3.3. Models Construction/ Parameters Settings 48
3.4. Training and Testing Using 5-fold Cross-validation 53
3.5. Rules Identification 55
3.5.1. Rules of Decision Trees 55
3.5.2. Comparison of Decision Trees and MLP Model 58
Chapter 4 Results 61
4.1. The Results of the MLP Models 61
4.2. The Results of the Rules of Decision Trees 64
4.2.1. The Best Classifier Selection Phase 64
4.2.2. Decision Trees Training Phase 64
4.2.3. Decision Trees Testing Phase 73
4.3. The Results of the Comparison of Decision Trees and MLP 80
4.3.1. The Best Classifier Selection Phase 80
4.3.2. MLP model Training Phase 80
4.3.3. MLP model Testing Phase 81
Chapter 5 Conclusions 83
5.1. Research Summary & Discussion 83
5.2. Research Constraints 85
5.3. Future Works 86
Appendix 87
Appendix A: Rate of Accuracy of 100 Classifiers in Predicting Upward Cases 87
References 88

Abowd, J. M. 1990. Does performance-based managerial compensation affect corporation performance? Industrial and Labor Relations Review 43(February): 52-73.
Anthony, J, H., and K. Ramesh. 1992. Association between accounting performance measures and stock prices, Journal of Accounting and Economics 15(4): 203-227.
Ayers, B. C., J. Jiang, and P. E. Yeung. 2006. Discretionary Accruals and Earnings Management: An Analysis of Pseudo Earnings Targets, The Accounting Review 81(3): 617-652.
Balsam, S. 1998. Discretionary accounting choices and CEO compensation. Contemporary Accounting Research 15 (Fall): 229-252.
Bartov, E., F. A. Gul, and J. Tsui. 2000. Discretionary-accruals models and audit qualifications. Journal of Accounting and Economics 30: 421-452.
Becker, C., M. Defond, J. Jiamobalvo, and K. Subramanyam. 1998. The effect of audit quality on earnings management. Contemporary Accounting Research 15: 1-24.
Beneish, M. 1997. How do managers benefit from earnings overstatement? Working paper, Indiana University.
Bergstresser, D. and T. Philippon. 2006. CEO incentives and earnings management. Journal of Financial Economics 80(3): 511-529.
Berry, M. and G. Linoff. 1997. Mastering data mining: the art and science of customer relationship management. 1st Edition. NY, USA: John Wiley & Sons, Inc.
Burgstahler, D. and M. Eames. 1998. Management of earnings and analysts forecasts. Working Paper, University of Washington.
Calderon, T. G., and J. J. Cheh. 2002. A roadmap for future neural networks research in auditing and risk assessment. International Journal of Accounting Information Systems 3: 203-236.
Chang, R.-D. and C.-J. Fang. 2006. Effects of the information disclosure and evaluation system on earnings management. The International Journal of Accounting Studies 42: 1-22.
Chang, W.-J. 2001. The effect of auditor’s quality on earnings management. Journal of Contemporary Accounting 2(2): 195-214.
Chang, W.-J., L.-T. Lynette Chou, and H.-W. William Lin. 2003. Consecutive changes in insider holdings and earnings management. The International Journal of Accounting Studies 37: 53-83.
Chen, J.-T., and Y.-H. Yeh. 2002. The Relationship between Corporate Restructuring, Corporate Governance and Earnings Management. The International Journal of Accounting Studies 34: 1-29.
DeAngelo, L. 1986. Accounting numbers as market valuation substitutes: a study of management buyouts of public stockholders. The Accounting Review 61: 400-420.
Dechow, P. and R. Sloan. 1991. Executive incentives and the horizon problem. Journal of Accounting and Economics 14: 51-89.
Dechow, P., R. Sloan, and A Sweeney. 1995. Detecting earning management. The Accounting Review 70 (April): 193-225.
Dechow, P., R. Sloan, and A Sweeney. 1996. Causes and Consequences of Earnings Manipulation: an Analysis of Firms Subject to Enforcement Actions By the SEC[J]. Contemporary Accounting Research 13(1): 1-36.
Degeorge, F., J. Patel, and R. Zechhauser. 1999. Earnings management to exceed thresholds. Journal of Business 72: 1-33.
FASB. 1984. Financial Accounting Concepts Statement No.5. Recognition and measurement in financial statements of business enterprises.
Fayyad U. and P. Stolorz. 1997. Data mining and KDD: promise and challenges[j]. Future Generation Computer Systems 13: 99-115.
Frankel, R. M., M. F. Johnson and K. K. Nelson. 2002. The relation between auditors’ fees for nonaudit services and earnings management. The Accounting Review 77: 71-105.
Garson, D. G. 1998. Neural networks: an introductory guide for social scientist. London: Sage Publications.
Guay, W. P., S. P. Kothari, and R. L. Watts. 1996. A market-based evaluation of discretionary accruals models. Journal of Accounting Research 34(Supplement): 83-105.
Haykin, S. 1994. Neural networks: a comprehensive foundation, 1st Edition. New Jersey: Prentice Hall.
Haykin, S. 1999. Neural networks: a comprehensive foundation, 2nd Edition. New Jersey: Prentice Hall.
Healy, P. 1985. The effect of bonus schemes on accounting decisions. Journal of Accounting and Economics 7: 85-107.
Healy, P., and J. Wahlen. 1999. A review of the earnings management literature and its implications for standard setting. Accounting Horizons 13(4): 365-383.
Jagielska, I., and J. Jaworski. 1996. Neural network for predicting the performance of credit card accounts. Computational Economics 9 (1): 77-82.
Jolliffe, I. T. 2002. Principal Component Analysis: Springer, New York, 2nd edition.
Jones, J. 1991. Earnings management during import relief investigations. Journal Accounting Research 29(2): 193-228.
Kasznik, R. 1999. On the association between voluntary disclosure and earnings management. Journal of Accounting Research 37: 57-82.
Kiani, M. Khurshid. 2005. Detecting business cycle asymmetries using artificial neural networks and time series models Computational Economics 26(1): 65.
Kumar, P.R. and V. Ravi. 2007. Bankruptcy prediction in banks and firms via statistical and intelligent techniques – A Review. European Journal of Operational Research 180: 1-28.
Lee, J.-Z., S.-W. Hsu, and J.-F. Chen. 2003. The Relationship between Non-Audit Services and Abnormal Accruals. The International Journal of Accounting Studies 37: 1-30.
Lee, S., S. Lee and Y. Park. 2007. A prediction model for success of services in e-commerce using decision tree: E-customer’s attitude towards online service. Expert Systems with Applications 33(3): 572-581.
Liao, Y.-H. 2004. On the Association between Board Independence, Firm Characteristics and Earnings Management. Unpublished Thesis, Department of Accounting, National Taipei University.
Lin, Kenny Z. 2006. The impact of tax holidays on earnings management: An empirical study of corporate reporting behavior in a developing-economy framework. The International Journal of Accounting 41(2): 163-175.
Lippmann, R. P. 1987. An introduction to computing with neural nets. IEEE ASSP Magazine April: 4-22.
Matsumoto, D. A. 2002. Management’s incentives to avoid negative earnings surprises. The Accounting Review 77(3): 483-514.
McCulloch, W. S. and W. Pitts. 1943. A logical calculus of the ideas imminent in nervous activity. Bulletin of Mathematical Biophysics 5: 115-137.
Min, J.-H. and Y.-C. Lee. 2005. Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert System with Applications 28: 603-614.
Odom, M. D., and R. Sharda. 1990. A neural network model for bankruptcy prediction. Paper read at International Joint Conference Neural Networks, June 17-21, 1990, at San Diego, CA.
Olmeda, I., and E. Fernandez. 1997. Hybrid classifiers for financial multi-criteria decision making: the case of bankruptcy prediction. Computational Economics 10 (4): 317-335.
Peasnell, K. V., P. F. Pope, and S. Young. 1999. Directors: Who are they? Accountancy 123:114.
Peláez, F. Rolando. 2006. Using neural nets to forecast the unemployment rate. Business Economics 41(1): 37-44.
Quinlan, J. R. 1993. Programs for Machine Learning. San Mateo, CA: Morgan Kaufmann.
Rajgopal, S., M. Venkatachalam, and J. Jiambalvo. 1999. Is institutional ownership associated with earnings management and the extent to which stock prices reflect future earnings? Working Paper, University of Washington at Seattle.
Roiger, R. J. and M. W. Geatz. 2003. Data mining: a tutorial-based primer. Boston MA: Addision Wesley.
Rumelhart, E. David, Geoffrey E. Hinton, and Ronald J. Williams. 1986a. Learning Representations by Back-propagating Errors. Nature 323: 533-536.
Rumelhart, E. David, Geoffrey E. Hinton, and Ronald J. Williams. 1986b. Learning Internal Representations by Error Propagation MIT Press Computational Models Of Cognition And Perception Series 1: 318-362.
Shiue, M.-J., and C.-J. Lin. 2004. The study of earnings management detecting models: a case of firms in financial distress. Taiwan Accounting Review 5(1): 105-130.
Spear, N. A., and M. Leis. 1997. Artificial neural networks and the accounting method choice in the oil and gas industry. Accounting Management & Information Technology 7 (3): 169-181.
Teoh, S. H., I. Welch, and T. J. Wong. 1998a. Earnings management and the post-issue performance of seasoned equity offerings. Journal of Financial Economics 50(October): 63-99.
Teoh, S. H., I. Welch, and T. J. Wong. 1998b. Earnings management and the long-run performance of initial public offerings. Journal of Finance 53: 1935-1974.
Vellido, A., P. Lisboa, and V. J. 1999. Neural networks in business: a survey of applications (1992-1998). Expert Systems with Applications 17: 51-70.
Wang, Hom-Ru. 1993. The empirical research of the effect of political cost and debt contract''s cost on firm''s accounting decision--the study of the positive accounting theory. Unpublished Thesis, National Sun Yat-Sen University. (in Chinese)
Watts, R. and J. L. Zimmerman. 1986. Positive theory of accounting. Englewood Cliffs, NY: Prentice-Hall.
Watts, R.L. &. J.L. Zimmerman. 1978. Towards a Positive Theory of the Determination of Accounting Standards. The Accounting Review 53(1): 112-134.
Witten, H., Ian, and Eibe Frank. 2005. Data mining: practical machine learning tools and techniques. California: Morgan Kaufman.
Wong, B. K., T. A. Bodnovich, and Y. Selvi. 1997. Neural networks applications in business: a review and analysis of the literature (1988-95). Decision Support Systems 19: 301-320.
Xie, B., W. N. Davidson and P. J. DaDalt. 2003. Earnings management and corporate governance: the role of the board and the audit committee. Journal of Corporate Finance 9: 295-316.
Xiong, Yan. 2006. Earnings management and its measurement: a theoretical perspective. Journal of American Academy of Business, Cambridge 9(1): 214-219.
Young, C.-S., and S.-J. Wu. 2003. CEO Pay-Performance Sensitivity, Performance Threshold and Discretionary Accounting Choices - An Empirical Study. The International Journal of Accounting Studies 36: 55-87.
Yu, Qiao, Bin Du and Qian Sun. 2006. Earnings management at rights issues thresholds—Evidence from China. Journal of Banking & Finance 30(12): 3453-3468.