Journal of the Korean Operations Research and Management Science Society (한국경영과학회지)

The Korean Operations Research and Management Science Society (한국경영과학회)
권호 표지

Utilization of Forecasting Accounting Earnings Using Artificial Neural Networks and Case-based Reasoning: Case Study on Manufacturing and Banking Industry

인공신경망과 사례기반추론을 이용한 기업회계이익의 예측효용성 분석 : 제조업과 은행업을 중심으로

  • Choe, Yongseok (Techno Management Graduate School of Korea Advanced Institute of Science and Technology) ;
  • Han, Ingoo (Techno Management Graduate School of Korea Advanced Institute of Science and Technology) ;
  • Shin, Taeksoo (Dept.of Business Administration Information, Yonsei University)
  • Published : 2003.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

The financial statements purpose to provide useful information to decision-making process of business managers. The value-relevant information, however, embedded in the financial statement has been often overlooked in Korea. In fact, the financial statements in Korea have been utilized for nothing but account reports to Security Supervision Boards (SSB). The objective of this study is to develop earnings forecasting models through financial statement analysis using artificial intelligence (AI). AI methods are employed in forecasting earnings: artificial neural networks (ANN) for manufacturing industry and case~based reasoning (CBR) for banking industry. The experimental results using such AI methods are as follows. Using ANN for manufacturing industry records 63.2% of hit ratio for out-of-sample, which outperforms the logistic regression by around 4%. The experiment through CBR for banking industry shows 65.0% of hit ratio that beats the statistical method by 13.2% in holdout sample. Finally, the prediction results for manufacturing industry are validated through monitoring the shift in cumulative returns of portfolios based on the earning prediction. The portfolio with the firms whose earnings are predicted to increase is designated as best portfolio and the portfolio with the earnings-decreasing firms as worst portfolio. The difference between two portfolios is about 3% of cumulative abnormal return on average. Consequently, this result showed that the financial statements in Korea contain the value-relevant information that is not reflected in stock prices.

Keywords

References

  1. Journal of Accounting Research v.15 no.Autumn The Time-Series Properties of Annual Earnings Albrecht,W.;L.Lookabill;J.Mckeown https://doi.org/10.2307/2490350
  2. Journal of Accounting Research v.6 no.2 An Empirical Evaluation of Accounting Income Numbers Ball,R.;P.Brown https://doi.org/10.2307/2490232
  3. Journal of Finance v.27 Some Time Series Properties of Accounting Income Ball,R.;Watt,R.L. https://doi.org/10.2307/2978268
  4. Journal of Accounting Research no.SUP. The Time-Series Behavior of Earnings Beaver,W.H.
  5. Financial Reporting : An Accounting Revolution(2nd ed.) Beaver,W.H.
  6. Journal of Finance v.31 no.5 Further Evidence of the Time Series Properties of Accounting Income Brooks,L.;D.Buckmaster https://doi.org/10.2307/2326685
  7. Intelligent Systems in Accounting, Finance and Management v.3 no.3 Applying Case-Based Reasoning to the Accounting Domain Brown,C.E.;U.G.Gupta https://doi.org/10.1002/j.1099-1174.1994.tb00066.x
  8. Journal of Finance v.33 no.1 The Superiority of Analyst Forecasts as Measures of Expectations : Evidence from Earnings Brown,L.D.;M.S.Rozeff https://doi.org/10.2307/2326346
  9. Internationa Journal of Forecasting v.12 no.4 Neural Network Forecasting of Quarterly Accounting Earnings Callen,J.L.;C.C.Y.Kwan;P.C.Y.Yip;Y.Yuan https://doi.org/10.1016/S0169-2070(96)00706-6
  10. Intelligent Systems in Accounting, Finance and Management v.5 The Prediction of Earnings Using Financial Statement information : Empirical Evidence with Logit Models and Artificial Neural Networks Charitou,A.;C.Charalambous https://doi.org/10.1002/(SICI)1099-1174(199612)5:4<199::AID-ISAF114>3.0.CO;2-C
  11. Valuation : Measuring and Managing the Value of Companies(2nd ed.) Copeland,T.E.;T.Koller;J.Murrin
  12. Journal of Accounting & Economics v.4 Financial Analyst's Forecasts of Earnings : A Better Surrogate for Market Expectations Fried,D.;D.Givoly https://doi.org/10.1016/0165-4101(82)90015-5
  13. Journal of Accounting & Economics v.15 no.2/3 The Prediction of Stock Returns Using Financial Statement Information Holthausen,R.W.;D.F.Larcker https://doi.org/10.1016/0165-4101(92)90025-W
  14. Journal of Accounting Research v.20 Analysis and Comparison of Earnings Forecast Agents Imhoff,G.;P.V. Pare https://doi.org/10.2307/2490750
  15. Accounting Review v.55 Further Evidence on the Accuracy of Management Forecasts vis-a-vis Analyst's Forecasts Jaggi,B.
  16. Journal of Accounting Research Discussion of the Time Series Properties of Accounting Earnings Jensen,M.C.
  17. The Accounting Review Some Additional Evidence on the Time Series Properties of Accounting Earnings Lookabill,L.
  18. Accounting Review v.51 A Comparative Examination of Management Forecasts and Box-Jenkins Forecasts of Earnings Lorek,K.S.;C.L.McDonald;D.H.Patz
  19. PhD Dissertation, Unverisity of Califonaia The Information Contents of Nonearnings Accounting Numbers as Earnings Predictors Ou,J.
  20. Journal of Accounting and Economics v.11 no.4 Financial Statement Analysis and the Prediction of Stock Returns Ou,J.;S.Penman https://doi.org/10.1016/0165-4101(89)90017-7
  21. Journal of Accounting Research no.Autumn Corporate Forecasts of Earnings per Share and Stock Price Behavior : Empirical Tests Patell,J.M.
  22. Proceedings of the Seminar on the Analysis of Security Prices Prediction of Investment Risk : Systematic and Residual Risk Rosenberg,B.;V.Marthe
  23. Decision Support Systems and Intelligent Systems(5th ed.) Turban,E.;J.E.Aronson
  24. Journal of Accounting Research v.15 The Time Series of Annual Accounting Earnings Watts,R.;R.Leftwich https://doi.org/10.2307/2490352
  25. Computer Systems That Learn - Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems Weiss,S.M.;C.A.Kulikowski