臺灣博碩士論文加值系統

股市預測仍然是一個具有挑戰性的問題，因為有很多因素影響股票市場價格，如公司新聞和業績，行業表現，投資者情緒，社交媒體情緒和經濟因素。這項工作使用Deep Convolutional Network和燭台圖表探討了股票市場的可預測性。結果用於設計決策支持框架，交易者可以使用該框架提供未來股票價格方向的建議指標。我們使用各種類型的神經網絡，如卷積神經網絡，殘差網絡和視覺幾何組網絡來完成這項工作。根據股市歷史數據，我們將其轉換為燭台圖表。之後，這些燭台圖表將作為輸入用於訓練卷積神經網絡模型。這種卷積神經網絡模型將幫助我們分析燭台圖表內的模式，並預測股市的未來走勢。利用台灣50和印尼10股票市場歷史時間序列數據，我們可以分別獲得有希望的結果 - 台灣和印度尼西亞股市的準確率分別為92.2％和92.1％。我們的績效結果明顯優於現有方法。

Stock market prediction is still a challenging problem because there are many factors effect to the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment and economic factors. This work explores the predictability in the stock market using Deep Convolutional Network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. After that, these candlestick charts will be feed as input for training a Convolution neural network model. This Convolution neural network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of stock market. Using Taiwan 50 and Indonesian 10 stock market historical time series data we can achieve a promising results- 92.2 % and 92.1 % accuracy for Taiwan and Indonesia stock market respectively. Our performance results significantly outperform the existing methods.

ABSTRACT ..................................................................................................................... iii
Acknowledgements .......................................................................................................... iv
Table of Contents .............................................................................................................. v
Table of Figures .............................................................................................................. vii
Table of Tables ............................................................................................................... viii
Chapter 1 Introduction ...................................................................................................... 1
1.1. Background ............................................................................................................ 1
1.1.1 Candlestick Chart .............................................................................................. 2
1.1.2 Candlestick Pattern ........................................................................................... 3
1.2. Related work ........................................................................................................... 7
Chapter 2 Data Collection ................................................................................................. 9
2.1. Data Collection using Yahoo! Finance .................................................................. 9
2.2. Time Series Data Feature Set ............................................................................... 12
2.2.1. Opening Price ................................................................................................ 13
2.2.2. Closing Price .................................................................................................. 13
2.2.3. Highest Price .................................................................................................. 13
2.2.4. Lowest Price .................................................................................................. 14
2.2.5. Volume........................................................................................................... 14
2.3. Data Preprocessing ............................................................................................... 14
Chapter 3 Methodology................................................................................................... 16
3.1. Chart Encoding ..................................................................................................... 16
3.2. Binary Classification ............................................................................................ 18
3.3. Learning Algorithm .............................................................................................. 18
3.3.1. Convolutional Neural Network ...................................................................... 18
3.3.2. Residual Network .......................................................................................... 20
3.3.3 VGG Network ................................................................................................. 22
3.3.4 Random Forest ................................................................................................ 23
3.3.5 K-Nearest Neighbors ...................................................................................... 24
3.4. Performance Evaluation ....................................................................................... 25
Chapter 4 Experimental Results and Discussion ............................................................ 26
4.1. Classification for Each Stock Market ................................................................... 26
4.1.1 Classification for Taiwan 50 dataset ............................................................... 26
4.1.2 Classification for Indonesia 10 dataset ........................................................... 31
v4.2. Independent testing result ..................................................................................... 35
4.3. Comparison .......................................................................................................... 37
Chapter 5 Conclusion and Future Works ........................................................................ 40
References ....................................................................................................................... 41

Malkiel, B.G. and E.F. Fama, Efficient capital markets: A review of theory and empirical
work. The journal of Finance, 1970. 25(2): p. 383-417.
Silver, D., et al., Mastering the game of Go with deep neural networks and tree search.
nature, 2016. 529(7587): p. 484-489.
Borovykh, A., S. Bohte, and C.W. Oosterlee, Dilated Convolutional Neural Networks for
Time Series Forecasting.
Morris, G.L., Candlestick Charting Explained: Timeless Techniques for Trading Stocks
and Futures: Timeless Techniques for Trading stocks and Sutures. 2006: McGraw Hill
Professional.
Lu, T.H., Y.M. Shiu, and T.C. Liu, Profitable candlestick trading strategies—The evidence
from a new perspective. Review of Financial Economics, 2012. 21(2): p. 63-68.
Schöneburg, E., Stock price prediction using neural networks: A project report.
Neurocomputing, 1990. 2(1): p. 17-27.
Bollen, J., H. Mao, and X. Zeng, Twitter mood predicts the stock market. Journal of
computational science, 2011. 2(1): p. 1-8.
do Prado, H.A., et al., On the effectiveness of candlestick chart analysis for the Brazilian
stock market. Procedia Computer Science, 2013. 22: p. 1136-1145.
Tsai, C.-F. and Z.-Y. Quan, Stock prediction by searching for similarities in candlestick
charts. ACM Transactions on Management Information Systems (TMIS), 2014. 5(2): p. 9.
Hu, G., et al., Deep Stock Representation Learning: From Candlestick Charts to Investment
Decisions. arXiv preprint arXiv:1709.03803, 2017.
Patel, J., et al., Predicting stock and stock price index movement using trend deterministic
data preparation and machine learning techniques. Expert Systems with Applications,
2015. 42(1): p. 259-268.
Khaidem, L., S. Saha, and S.R. Dey, Predicting the direction of stock market prices using
random forest. arXiv preprint arXiv:1605.00003, 2016.
Zhang, X., et al., Improving stock market prediction via heterogeneous information fusion.
Knowledge-Based Systems, 2018. 143: p. 236-247.
Hunter, J.D., Matplotlib: A 2D graphics environment. Computing in science &
engineering, 2007. 9(3): p. 90-95.
He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE
conference on computer vision and pattern recognition. 2016.
Krizhevsky, A., I. Sutskever, and G.E. Hinton. Imagenet classification with deep
convolutional neural networks. in Advances in neural information processing systems.
2012.
Zeiler, M.D. and R. Fergus. Visualizing and understanding convolutional networks. in
European conference on computer vision. 2014. Springer.
Szegedy, C., et al. Inception-v4, inception-resnet and the impact of residual connections
on learning. in AAAI. 2017.
Simonyan, K. and A. Zisserman, Very deep convolutional networks for large-scale image
recognition. arXiv preprint arXiv:1409.1556, 2014.
4120.
Pedregosa, F., et al., Scikit-learn: Machine learning in Python. Journal of machine learning
research, 2011. 12(Oct): p. 2825-2830.
Wongbangpo, P. and S.C. Sharma, Stock market and macroeconomic fundamental
dynamic interactions: ASEAN-5 countries. Journal of Asian Economics, 2002. 13(1): p.
27-51.