Applications of Trading Strategies for Convolution Neural Network and Technical Indicators in Taiwan Stock Price Index Futures

• Main Authors: Lee, Chieh-Ying, 李杰穎
• Other Authors: Lin, Shih-Kuei
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/7t85cf

碩士 === 國立政治大學 === 金融學系 === 107 === In terms of financial trading, it is possible to achieve automatically placing orders through following several technical indicators. In this paper, we apply Convolutional Neural Networks to the technical trading strategy. We converted opening price, highest price, closing price, lowest price, and the trend of technical indicator into images. We hoped that by the excellent ability of image recognition of Convolutional Neural Networks, we can extract the features of profit strategies and loss strategies, and then improve the accuracy of trading strategies. The empirical results show that no matter long strategies or short strategies were used, after the training of Convolutional Neural Networks, the accuracy of gaining profits from the strategies can be improved effectively. In recent years, people in Taiwan pay more and more attention to the development of artificial intelligence combined with financial services. My expectation is to provide different ideas to scholars and experts who worked hard in this related area in this thesis, so that they might further develop new techniques in this area from different perspectives.