本論文目的在於比較時間序列模型（自我回歸整合移動平均以及轉換函數模型）與人工智慧模式（類神經網路以及基因演算法）對季每股盈餘的預測能力。比較的觀點有二：一為估計值與實際值的偏離程度，二為預測方向的準確性。不論在偏離程度或是方向準確性方面，基因演算法皆優於轉換函數模型與類神經網路。
　　此外，本論文亦考慮利用稀釋後每股盈餘來預測基本每股盈餘的預測能力，但因樣本公司潛在性稀釋證券轉換比率偏低，故在本研究中未能顯著證明稀釋後每股盈餘相對於基本每股盈餘而言，具有較佳的預測能力。

　　The purpose of this study is to compare the forecasting ability among the ARIMA model, the Transfer Function model, the Artificial Neural Network model and the Genetic Algorithm model. To evaluate the forecasting accuracy, there are two dimensions taken into consideration: 1) the deviation between the actual quarterly EPS value and the forecasted quarterly EPS value, and 2) the changing direction from quarter to quarter between the actual quarterly EPS value and the forecasted quarterly EPS value.
　　In the aspect of the deviation between the actual quarterly EPS value and the forecasted quarterly EPS value, the empirical results show that the Transfer Function model outperforms the ARIMA model. Therefore, the settings of time lags of the Transfer Function model are adopted to the other two models. The empirical results reveals that the Genetic Algorithm model shows the best forecasting accuracy in both dimensions while the Artificial Neural Network model shows the worst forecasting accuracy in both dimensions.
　　In addition, both of the quarterly basic EPS data and the quarterly diluted EPS data were applied in forecasting future quarterly basic EPS. There is not enough evidence to support that using the diluted EPS data would yield higher accuracy than using the basic EPS data in the aspect of deviation. However, the empirical result shows that using the basic EPS data outperforms using the diluted EPS to forecast future basic EPS in the aspect of predicting the directions.

Bathke, A.W. Jr. and K.S. Lorek. 1984. The relationship between time-series models and the security market’s expectation of quarterly earnings. The Accounting Review, 59: 163-177.

Bradley, Wray E.. 2003. Improving Quarterly Earnings Estimates: The Predictive Ability of the Cash Reinvestment Ratio. Journal of American Academy of Business, Cambridge: 549-553.

Brown, L. and M. Rozaff. 1979. Univariate Time-Series Models of Quarterly Accounting Earnings Per Share: A Proposed Model. Journal of Accounting Research, 17(1): 179-189.

Callen, Jeffrey L., Clarence C.Y. Kwan, Patrick C.Y. Yip and Yufei Yuan. 1996. Neural network forecasting of quarterly accounting earnings. International Journal of Forecasting 12: 475-482.

Chen, Jan-Chu. 1995. Forecast Future Earnings Per Share Using Financial Ratios. Graduate Institute of Accounting, National Cheng Kung University.

Chua, C.G. and A. T. C. Goh. 2003. A Hybrid Bayesian Back-Propagation Neural Network Approach to Multivariate Modeling. International Journal for Numerical and Analytical Methods in Geomechanics 27: 651-667.

Coakley, James R. and Carol E. Brown. 2000. Artificial Neural Networks in Accounting and Finance: Modeling Issues. International Journal of Intelligent Systems in Accounting, Finance & Management 9: 119-144.

Collins, William A. and William S. Hopwood. 1980. A Multivariate Analysis of Annual Earnings Forecasts of Generated from Quarterly Forecasts of Financial Analysts and Univariate Time-Series Models. Journal of Accounting Research 18 (2): 390-406

Dechow, Patricia M., S.P. Kothari and Ross L. Watts. 1998. The Relation between Earnings and Cash Flows. Journal of Accounting and Economics 25: 133-168.

Foster, George. 1977. Quarterly Accounting Data: Time-Series Properties and Predictive Ability Results. The Accounting review: 1-21.

Hill, Tim, Marcus O’ Connor and William Remus. 1996. Neural Network Models for Time Series Forecasts. Management Science: 1082-1092.

Lai, Syouching. 1998. The Prediction of Material Dilution Effect from Potentially Dilutive Securities on EPS. Journal of National Cheng Kung University. Vol.33.

Lawrence, Kryzanowski, Michael Galler and David W. Wright. 1993. Using Artificial Neural Networks to Pick Stocks. Financial Analysts Journal: 21-27.

Leigh, William, Russell Purvis and James M. Ragusa. 2002. Forecasting the NYSE composite index with technical analysis, pattern recognizer, neural network, and genetic algorithm: a case study in romantic decision support. Decision Support Systems 32: 361-377.

Li, Hing-Chih. 1991. The Interrelationship between Domestic and External Markets Using Eurodollar Futures and Treasure Bill Futures. Graduate Institute of Finance, Southern Illinois University.

Liu, Bo-Xuan. 1998. The Relationship between Fundamental Analysis and Earnings Forecast. Graduate Institute of Accounting, National Taiwan University.

Lobo, Gerald J. and R.D. Nair. 1990. Combining Judgmental and Statistical Forecasts: An Application to Earnings Forecasts. Decision Sciences: 446-460.

Moutinho, Hurley, S. and N.M. Stephens. 1995. Solving marketing optimization problems using genetic algorithms. European Journal of Marketing. 39-56.

Niculescu, Stefan P.. 2003. Artificial neural networks and genetic algorithms in QSAR. Journal of Molecular Structure 622: 71-83.

SAS/ETS User’s Guide. Version 5 Edition.

Slavin, Nathan and J.K.Yun. 2001. Earnings per share: A Review of the New accounting Standard. The Journal of Corporate Accounting & Finance: 57-71.

Tsai, Yuh-Ching. 1994. An Empirical Investigation of the Association between Financial Ratios and Earnings Per Share. Graduate Institute of Accounting, National Taiwan University.

Yu, Wen-Chang. EPS Forecast--Using the Neuro Network. Graduate Institute of Financial Management, National Sun Yat-Sen University.