Main Article Content
This study focuses on accrual-based earnings management. The purpose of this study is to establish an innovative and high-accuracy model for detecting earnings management using hybrid machine learning methods integrating stepwise regression, elastic net, logistic regression (Logit regression), and decision tree C5.0. Samples of this study are the electronic companies listed on the Taiwan Stock Exchange, and data are derived from the Taiwan Economic Journal (TEJ) for a period of ten years from 2008 to 2017. Results show that the earnings management detection model, as established by elastic net and C5.0, provides the best classification performance, and its average accuracy reaches 97.32%.
Gunny KA. The relation between earnings management using real activities manipulation and future performance: Evidence from meeting earnings benchmarks. Cont. Account. Res. 2010;27: 855-888.
Shahzad A. Detecting earnings management and earnings manipulation in BRIC countries; a panel data analysis for post global financial crisis period. Int. J Account Res. 2016;4:1-10.
Dechow PM, Sloan RG, Sweeney AM. Detecting earnings management. Account. Rev. 1995;70:193-225.
Chen FH, Chi DJ, Wang YC. Detecting biotechnology industry's earnings management using Bayesian network, principal component analysis, back propagation neural network and decision tree. Econ. Modell. 2015;46:1-10.
Schipper K. Commentary on earnings management. Account Horiz. 1989;3:91-102.
Davidson S, Stickney C, Weil R. Accounting: The language of business, 7th Ed. Sun Lakes, Ariz.: T. Horton; 1987.
Healy P, Palepu K. Effectiveness of accounting-based debt covenants. J. Account. Econ. 1990;12:97-123.
Doyle JT, Jennings J, Soliman MT. Do managers define Non-GAAP earnings to meet or beat analyst forecasts? J. Account. Econ. 2013;56:40-56.
Cohen DA, Zarowin P. Accrual-based and real earnings management activities around seasoned equity offerings. J. Account. Econ. 2010;50:2-19.
McVay SE. Earnings management using classification shifting: An examination of core earnings and special items. Account. Rev. 2006;81:501-531.
Cohen DA, Dey A, Lys TZ. Real and accrual-based earnings management in the Pre- and Post-Sarbanes-Oxley periods. Account. Rev. 2008;83:757-787.
Roychowdhury S. Earnings management through real activities manipulation. J. Account. Econ. 2006;42:335-370.
Dechow PM, Sloan RG, Hutton AP, Kim JH. Detecting earnings management: A new approach. J. Account. Res. 2012;50: 275-334.
Healy PM. The effect of bonus schemes on accounting decisions. J. Account. Econ. 1985;7:85-107.
Höglund H. Detecting earnings management with neural networks. Expert. Syst. Appl. 2012;39:9564-9570.
Jones JJ. Earnings management during import relief investigations. J. Account. Res. 1991;29:193-228.
Kothari SP, Leoneb AJ, Wasley CE. Performance matched discretionary accrual measures. J. Account. Econ. 2005;39:163-197.
Gupta R, Modise MP. South African stock return predictability in the context data mining: The role of financial variables and international stock returns. Econ. Model. 2012;29:908-916.
Zou H, Hastie T. Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B Stat. Methodol. 2005;67:301-320.
Tibshirani R. Regression shrinkage and selection via the Lasso. J. Roy Stat Soc B Met. 1996;58:267-288.
Alberto TB, Carlo M, Jose RD. V-SVM solutions of constrained lasso and elastic net. Neurocomputing. 2018;275:1921-1931.
Chen S, Hou J, Xiao D. One belt, one road; initiative to stimulate trade in China: A counter-factual analysis. Sustainability. 2018;10:3242-3254.
Frank E, Matthias D. High-dimensional LASSO-based computational regression models: Regularization, shrinkage and selection. Mach. Learn. Knowl. Extr. 2019;1:359-383.
Katrutsa AM, Strijov VV. Stress test procedure for feature selection algorithms. Chemometr Intell Lab. 2015;142:172- 183.
Katrutsa AM, Strijov VV. Comprehensive study of feature selection methods to solve multicollinearity problem according to evaluation criteria. Expert Syst Appl. 2017;76:1-11.
Viaene S, Dedene G, Derrig RA. Auto claim fraud detection using Bayesian learning neural networks. Expert Syst Appl. 2005;29:653-666.
Efron B, Hastie T, Johnstone I, Tibshirani R. Least angle regression. Ann Stat. 2004;32:407-499.
Quinlan JR. Introduction of decision trees. Mach. Learn. 1986;1:81-106.
Kotsiantis S, Koumanakos E, Tzelepis D, Tampakas V. Forecasting fraudulent financial statements using data mining. Int. J. Comput. 2006;3:104-110.
Jan CL. An effective financial statements fraud detection model for the sustainable development of financial markets: Evidence from Taiwan. Sustainability. 2018;10:1-14.
Chen S, Goo YJ, Shen ZD. A hybrid approach of stepwise regression, logistic regression, support vector machine and decision tree for forecasting fraudulent financial statements. Sci. World J.; 2014.
Goo YJ, Chi DJ, Shen ZD. Improving the prediction of going concern of Taiwanese listed companies using a hybrid of LASSO with data mining techniques. Springer Plus; 2016.
Hall M, Holmes G. Benchmarking attribute selection techniques for discrete class data mining. IEEE T Knowl Data En. 2003;15: 1437-1447.
Huberty CJ. Problems with stepwise methods-better alter-natives. Adv Soc Sci Meth. 1989;1:43-70.
Chen S. An effective going concern prediction model for the sustainability of enterprises and capital market development. Appl. Econo. 2019;51:3376-3388.
Yeh CC, Chi DJ, Lin YR. Going concern prediction using hybrid random forests and rough set approach. Inf. Sci. 2014;254:98-110.