圖形辨識在現今是一個很熱門的議題，但較少應用在財務領域方面。本篇論文主要是將股票市場的技術指標與籌碼面等時間序列資料轉成2D圖片，藉由圖片，歸納人類的投資行為，來預測趨勢的轉折點以及所能帶來的收益率。2D圖片的大小為15x15，包含12種不同間隔參數的技術指標以及3種加入落後期的籌碼面資料，並利用歷史股價結合zigzag指標找出趨勢的轉折點，納入卷積神經網絡模型(CNN)與長短期記憶模型(LSTM)做為訓練。再經由穩健性測試與回測績效來觀察策略的可行性。最後，加入資金控管以及考慮市場上的流通性，利用回測結果仿造成立一檔基金，該基金的年化報酬與勝率分別為8.13%與62.26%，且績效於2010年至2018年的走勢皆明顯優於元大台灣50指數型基金。

Pattern recognition is now all the rage, but seldom be used in the field of finance. The purposes of this study were to convert financial time series such as technical indicators and chip data into 2-D images and predict the inflection points of stock price by training the Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model. The size of the 2-D images which include twelve kinds of technical indicators each with different parameter and three kinds of chip data is 15x15. The inflection points were calculated by Zigzag indicator using historical stock price. In order to know the feasibility of the strategy, this study used the robustness check and backtest. Finally, over the last 9 years, considering funds management and market liquidity, the results of the strategy which annualized return and win rate were 8.13% and 62.26% outperformed the benchmark.

論文審定書　　i
摘　　要　　ii
Abstract　　iii
目　　錄　　iv
圖　　次　　vi
表　　次　　viii
第一章　緒論 1
第一節　研究動機 1
第二節　研究目的 2
第二章　文獻探討 3
第一節 技術面分析 3
第二節　籌碼面分析 4
第三節　深度學習 5
第四節　圖形辨識於股票市場上的應用 6
第三章　研究方法 7
第一節　樣本與研究期間 7
第二節　標籤定義 7
第三節　圖片生成 10
第四節　卷積神經網路模型 16
第五節　長短期記憶模型 19
第四章　實證結果 23
第一節　穩健性檢驗 23
第二節　策略績效 34
第五章　結論與建議 42
第一節　結論 42
第二節　後續建議 43
參考文獻 44
第一節 中文文獻 44
第二節 英文文獻 45

王月玲(2003)，「外資對台灣股市的影響」，碩士論文，國立政治大學金融研究所。
陳彥豪(2002)，「外資與投信法人持股比率變化對股價報酬率影響之研究－以上市電子股為例」，碩士論文，國立中山大學財務管理學研究所。
陳俊豪(2017)，「利用卷積神經網路深度學習方法預測外匯走勢」，碩士論文，國立臺灣大學經濟學研究所。
陳子軒(2018)，「運用基本面、技術面及籌碼面建構台股深度學習交易策略」，碩士論文，國立中山大學金融創新產業碩士專班。
洪宇凡(2018)，「長短期記憶模型預測元大台灣卓越50基金之研究」，碩士論文，國立高雄第一科技大學金融系碩士班。
吳哲緯(2017)，「使用深度學習卷積神經網路預測股票買賣策略之分類研究」，碩士論文，國立中山大學資訊管理學系研究所。
賴嘉蔚(2018)，「卷積神經網路預測時間序列能力分析」，碩士論文，國立政治大學金融學系研究所。

Graves, A. (2012). Supervised Sequence Labelling with Recurrent Neural Networks. Textbook, Studies in Computational Intelligence, Springer.
Bisoi, R., Dash, P. (2014). A hybrid evolutionary dynamic neural network for stock market trend analysis and prediction using unscented Kalman filter. Applied Soft Computing, 19, 41–56.
Chen, K., Zhou, Y., Dai, F. (2015). A LSTM-based method for stock returns prediction: A case study of China stock market. IEEE International Conference on Big Data, 2015, 2823-2824.
Ferreira, M., Matos, P., Pereira, J., Pires, P. (2017). Do locals know better? A comparison of the performance of local and foreign institutional investors. Journal of Banking & Finance, 82, 151-164.
Fischer, T., Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270, 654-669.
Hinton, G., E., Salakhutdinov, R., R. (2006). Reducing the dimensionality of data with neural networks. Science, 313, 504-507.
Ko, K. C., Lin, S.J., Su, H. J., Chang, H. H. (2014). Value investing and technical analysis in Taiwan stock market. Pacific-Basin Finance Journal, 26, 14-36.
Murphy, J. J. (1999). Technical analysis of the financial markets: A comprehensive guide to trading methods and applications: Prentice Hall Press.
Murugan, P. (2017). Feed Forward and Backward Run in Deep Convolution Neural Network. Nanyang Technological University. School of Mechanical and Aerospace Engineering.
Roondiwala, M., Patel, H., Varma, S. (2017). Predicting stock prices using LSTM. International Journal of Science and Research, 6(4), 1754-1756.
Stankovic, J., Markovic, I., Stojanovic, M. (2015). Investment strategy optimaiztion using technical analysis and predictive modeling in emerging markets. Procedia Economics and Finance, 19, 51-62.
Sezer, O. B., Ozbayoglu, A. M. (2018). Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach. Applied Soft Computing, 70, 525-538.
Ticknor, J. L. (2013). A Bayesian regularized artificial neural network for stock market forecasting. Expert Systems with Applications, 40, 5501–5506.
Wang, J., Hou, R., Wang, C., Shen, L. (2016). Improved v-Support vector regression model based on variable selection and brain storm optimization for stock price forecasting. Applied Soft Computing, 49, 164-178.
Zou, L., Tang, T., Li, X. (2016). The stock preferences of domestic versus foreign investors: Evidence from Qualified Foreign Institutional Investors (QFIIs) in China. Journal of Multinational Financial Management, 37-38, 12-28.