訓練期視窗大小四年統整結果

下圖三十一及表二十一為利用訓練期四年資料訓練後的選股模型，並將測試 期一至五年資料放入選股模型後的勝率圖及勝率表，在圖中看見 LSTM 選股模 型面對五項指標的勝率，隨著測試期長度的增長LSTM 選股模型勝率愈高，平均 勝率高達八成五以上。

訓練期長度四年，測試期長度一至五年之LSTM VS. 五項指標勝率圖 訓練期長度四年，測試期長度一至五年之LSTM VS. 五項指標勝率表

測試期長度 一年 二年 三年 四年 五年

指標名稱 次數 勝率 次數 勝率 次數 勝率 次數 勝率 次數 勝率 本益比 88 92% 82 98% 71 99% 60 100% 47 98%

股價淨值比 82 85% 81 96% 70 97% 59 98% 47 98%

股價營收比 93 97% 84 100% 72 100% 60 100% 47 98%

現金殖利率 56 58% 71 85% 64 89% 56 93% 44 92%

台指大盤 81 84% 76 90% 72 100% 60 100% 48 100%

總TV 數 96 100% 84 100% 72 100% 60 100% 48 100%

44

4.6.20 訓練期視窗大小五年統整結果

下圖三十二及表二十二為利用訓練期五年資料訓練後的選股模型，並將測試 期一至五年資料放入選股模型後的勝率圖及勝率表，在圖中看見 LSTM 選股模 型面對五項指標的勝率，隨著測試期長度的增長LSTM 選股模型勝率愈高，平均 勝率高達八成五以上。

訓練期長度五年，測試期長度一至五年之LSTM VS. 五項指標勝率圖 訓練期長度五年，測試期長度一至五年之LSTM VS. 五項指標勝率表

測試期長度 一年 二年 三年 四年 五年

指標名稱 次數 勝率 次數 勝率 次數 勝率 次數 勝率 次數 勝率 本益比 78 93% 71 99% 60 100% 47 98% 36 100%

股價淨值比 70 83% 66 92% 58 97% 48 100% 36 100%

股價營收比 82 98% 72 100% 60 100% 48 100% 36 100%

現金殖利率 54 64% 56 78% 55 92% 47 98% 34 94%

台指大盤 70 83% 66 92% 60 100% 48 100% 36 100%

總TV 數 84 100% 72 100% 60 100% 48 100% 36 100%

45

本研究一共做了25 種不同實驗的結果，藉由上述圖十三至圖二十七以及表 三至表十七，可以發現 LSTM 選股模型在不同實驗結果中可以贏過大部分的指 標選股模型，藉由圖二十八至圖三十二以及表十八至表二十二，可以詳細看到 LSTM 各別對五項指標的勝率比較圖，也可看見 LSTM 在訓練期愈長且測試期 愈長的情況下皆幾乎贏過五項指標，且在測試期五年時勝率不小於九成。

46

47

6. 參考文獻

[1] B. Graham, and D. Dodd. Security=Analysis.McGraw-Hill, 1934.

[2] A. Kane, A. Marcus, and J. Noh, “The P/E multiple and market volatility,” Financial=

Analyst=Journal, vol. 52, no.4, pp. 16-24, 1996.

[3] J. Lakonishok, A. Shleifer, and R.W. Vishny, “Contrarian investment, extrapolation, and risk,” Journal=of=Finance, vol. 49(5) , pp. 1541-1578, 1994.

[4] P. Sareewiwatthana, “Common financial ratios and value investing in Thailand,”

Journal=of=Finance=and=Investment=Analysis, vol. 2, no.3, pp. 69-85, 2013.

[5] M.J. Gordon, “Optimal investment and financing policy,” Journal=of=Finance, vol. 18, no. 2, pp. 264-272, 1963.

[6] J. Barhak, and A. Ficher, “Parameterization and reconstruction from 3D scattered points based on neural network and PDE techniques,” IEEE=Transactions=on=Visualization=and=

Computer=Graphics, vol. 7, no. 1, pp. 1-16, 2001.

[7] R. Collobert, and J. Weston, “A unified architecture for natural language processing:

deep neural networks with multitask learning,” in Proceedings= of= the= 25th= = International=Conference=on=Machine=learning, pp.160-167, 2008.

[8] Y. Bengio, R. Ducharme, P. Vincent, and C. Janvin, “A neural probabilistic language model,” The=Journal=of=Machine=Learning=Research, vol. 3, no.6, pp. 1137-1155, 2003.

[9] S. X. Wu, and W. Banzhaf “The use of computational intelligence in intrusion detection systems: a review,” Applied=Soft=Computing, vol. 10, no. 1 , pp. 1-35, 2010.

[10] A. Graves, A. Mohamed, and G. Hinton, “Speech recognition with deep recurrent neural networks,” The=2013=IEEE=International=Conference=on=Acoustics,=Speech=and=

Signal=Processing, Canada, 2013.

[11] G. Hinton, L. Deng, D. Yu, G. E. Dahi, A. Mohamed, N. Jailty, A. Senior, V.

Vanhoucke, P. Nguyen, T. N. Sainath, and B. Kingbury, “Deep neural networks for

48

acoustic modeling in speech recognition: The shared views of four research groups,”

IEEE=Signal=Processing=Magazine, vol. 29, no. 6, pp. 82-97, 2012.

[12] B. K. Wang, and Y. Selvi, “Neural network applications in finance: A review and analysis of literature (1990–1996),” Information= &= Management, vol. 34, no. 3, pp.

129-139, 1998.

[13] A. Fadlalla, and C.-H. Lin, “An analysis of the applications of neural networks in finance,” Interfaces, vol. 31, no. 4, pp. 112-122, 2001.

[14] Y. Li, and W. Ma, “Applications of artificial neural networks in financial economics:

A survey,”= The= 2010= International= Symposium= on= Computational= Intelligence= and=

Design, Hangzhou, pp. 211-214, doi: 10.1109/ISCID.2010.70, 2010.

[15] C.-F. Huang, C.-J. Hsu, C.-C. Chen, B.-R. Chang, and C.-A. Li (2015). “An intelligent model for pairs trading using genetic algorithms,” Computational=

intelligence= and= Neuroscience. vol.2015, Article ID 939606, 10pages,

doi:10.1155/2015/939606, 2015.

[16] E. Tsang, P. Yung, and J. Li, “EDDIE-automation, a decision support tool for financial forecasting,” Decision=Support=Systems, vol. 37, no. 4, pp. 559–565, 2004.

[17] F. Varetto, “Genetic algorithms applications in the analysis of insolvency risk,”=

Journal=of=Banking=&=Finance, vol. 22, no. 10-11, pp. 1421–1439, 1998.

[18] A. Gaspar-Cunha, G. Recio, L. Costa, and C. Estebanez, “Self-adaptive MOEA feature selection for classification of bankruptcy prediction data,” The=Scientific=World=

Journal, vol. 2014, Article ID 314728, 20 pages, 2014.

[19] M. Lam, “Neural network techniques for financial performance prediction: integrating fundamental and technical analysis” Decision= Support= Systems, pp. 567-581, September 2004.

[20] L. Kryzanowski, M. Galler, and D. W. Wright, “Using artificial neural networks to

49

pick stocks,” Financial=Analysts=Journal, vol. 49, no. 4, pp. 21-27, 1993.

[21] T.-J. Hsieh, H.-F. Hsiao, and W.-C. Yeh, “Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm,” Applied=Soft=Computing, vol. 11, no. 2, pp. 2510-2525, 2011.

[22] C. Chalvatzis, and D. Hristu-Varsakelis, “High-performance stock index trading:

making effective use of a deep LSTM neural network , “ Papers 1902.03125,=arXiv.org, May 2019.

[23] F. Kamalov, “Forecasting significant stock price changes using neural networks,” Papers 1912.08791,=arXiv.org, 2019.

[24] C.-F. Huang, “A hybrid stock selection model using genetic algorithms and support vector regression,” Applied=Soft=Computing , vol. 12, no. 2, pp. 807–818, 2012.

[25] S. Haykin, Neural=Networks:=A=Comprehensive=Foundation. Upper Saddle River, NJ:

Prentice Hall, 1994.

[26] P. Rilstone, V.K. Srivastava, and A. Ullah, “The second-order bias and mean squared error of nonlinear estimators,”=Journal=of=Econometrics, vol. 75, pp. 369-395, 1996.

[27] D. P. Kingma, and J. L. Ba, “Adam: A method for stochastic optimization.”= arXiv=

preprint=arXiv:1412.6980, 2014.

[28] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, pp. 533-536, 1986.

[29] S. Hochreiter, and J. Schmidhuber, “Long short-term memory,” Neural=

Computation, vol. 9, no. 8, pp. 1735-1780, 1997.

[30] C.-F. Huang, and H.-C. Li, “An evolutionary method for financial forecasting in microscopic high-speed trading environment,” Computational= Intelligence= and=

Neuroscience, vol. 2017, pp. 1-18, 2017.