Publications-Theses
Article View/Open
Publication Export
-
題名 卷積神經網路於黃金期貨技術指標投資之應用
Application of Convolutional Neural Network on Gold Future Technical Index作者 蔡宛伶
Tsai, Wan-Ling貢獻者 林士貴<br>蔡銘峰
Lin, Shih-Kuei<br>Tsai, Ming-Feng
蔡宛伶
Tsai, Wan-Ling關鍵詞 卷積神經網路
深度學習
技術分析
技術指標
黃金期貨
Convolutional Neural Network
Deep Learning
Technical Analysis
Technical Index
Gold Future日期 2020 上傳時間 1-Jul-2020 13:41:00 (UTC+8) 摘要 本文探討卷積神經網路與技術指標結合之黃金期貨交易投資策略，以黃金期貨的技術線圖作為模型訓練資料，篩選出報酬率夠高的交易訊號，達成精準投資之目的。在資本市場當中，許多人憑藉著技術分析資訊找出股價波動的規律，但除了傳統的數值資料之外，技術分析當中還有許多技術線圖，提供我們具象化的資訊，這些圖像資訊遂成為非常重要的投資決策依據。深度學習在近十年中有非常顯著的成長，其中的卷積神經網路尤其在圖像辨識領域有長足的突破，如今卷積神經網路已成為主流圖像辨識所使用的方法，因此本文應用卷積神經網路，透過技術分析中大量的技術線圖，旨在分類出具有獲利潛力的交易訊號。
This article is mainly about applying convolutional neural networks to gold futures technical indicators trading strategy. The technical indicator graph of gold futures is used as model training data to screen out trading signals with a high return rate, aiming to increase average return.In the capital market, many people rely on technical analysis to find out the pattern of stock price. In addition to traditional numerical data, there are many technical indicator graphs could provide specific information. The image information is then become a very important basis for investment decisions.Deep learning has grown significantly in the past decade. Among all kinds of deep learning models, the convolutional neural network has achieved a great performance on image recognition. This article applied convolutional neural networks to technical analysis by using technical indicator graphs, aiming to classify trading signals with potential high-profit.參考文獻 一、中文文獻[1] 李杰穎. (2019). 卷積神經網路結合技術指標交易策略在台灣加權指數期貨之應用.[2] 劉昭雨，2017，卷積神經網路在金融技術指標之應用二、英文文獻[3] Malkiel, B. G., & Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), 383-417.[4] Brock, W., Lakonishok, J., & LeBaron, B. (1992). Simple technical trading rules and the stochastic properties of stock returns. The Journal of finance, 47(5), 1731-1764.[5] Pruitt, S. W., & White, R. E. (1988). The CRISMA Trading System: Who Says Technical Analysis Can`. Journal of Portfolio Management, 14(3), 55.[6] Tsai, C. F., & Wang, S. P. (2009, March). Stock price forecasting by hybrid machine learning techniques. In Proceedings of the international multiconference of engineers and computer scientists (Vol. 1, No. 755, p. 60).[7] Di Persio, L., & Honchar, O. (2016). Artificial neural networks architectures for stock price prediction: Comparisons and applications. International journal of circuits, systems and signal processing, 10(2016), 403-413.[8] Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2017, July). Forecasting stock prices from the limit order book using convolutional neural networks. In 2017 IEEE 19th Conference on Business Informatics (CBI) (Vol. 1, pp. 7-12). IEEE.[9] Pyo, S., Lee, J., Cha, M., & Jang, H. (2017). Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets. PloS one, 12(11).[10] Alexander, S. S. (1961). Price movements in speculative markets: Trends or random walks. Industrial Management Review (pre-1986), 2(2), 7. 描述 碩士
國立政治大學
金融學系
107352006資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107352006 資料類型 thesis dc.contributor.advisor 林士貴<br>蔡銘峰 zh_TW dc.contributor.advisor Lin, Shih-Kuei<br>Tsai, Ming-Feng en_US dc.contributor.author (Authors) 蔡宛伶 zh_TW dc.contributor.author (Authors) Tsai, Wan-Ling en_US dc.creator (作者) 蔡宛伶 zh_TW dc.creator (作者) Tsai, Wan-Ling en_US dc.date (日期) 2020 en_US dc.date.accessioned 1-Jul-2020 13:41:00 (UTC+8) - dc.date.available 1-Jul-2020 13:41:00 (UTC+8) - dc.date.issued (上傳時間) 1-Jul-2020 13:41:00 (UTC+8) - dc.identifier (Other Identifiers) G0107352006 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/130541 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 金融學系 zh_TW dc.description (描述) 107352006 zh_TW dc.description.abstract (摘要) 本文探討卷積神經網路與技術指標結合之黃金期貨交易投資策略，以黃金期貨的技術線圖作為模型訓練資料，篩選出報酬率夠高的交易訊號，達成精準投資之目的。在資本市場當中，許多人憑藉著技術分析資訊找出股價波動的規律，但除了傳統的數值資料之外，技術分析當中還有許多技術線圖，提供我們具象化的資訊，這些圖像資訊遂成為非常重要的投資決策依據。深度學習在近十年中有非常顯著的成長，其中的卷積神經網路尤其在圖像辨識領域有長足的突破，如今卷積神經網路已成為主流圖像辨識所使用的方法，因此本文應用卷積神經網路，透過技術分析中大量的技術線圖，旨在分類出具有獲利潛力的交易訊號。 zh_TW dc.description.abstract (摘要) This article is mainly about applying convolutional neural networks to gold futures technical indicators trading strategy. The technical indicator graph of gold futures is used as model training data to screen out trading signals with a high return rate, aiming to increase average return.In the capital market, many people rely on technical analysis to find out the pattern of stock price. In addition to traditional numerical data, there are many technical indicator graphs could provide specific information. The image information is then become a very important basis for investment decisions.Deep learning has grown significantly in the past decade. Among all kinds of deep learning models, the convolutional neural network has achieved a great performance on image recognition. This article applied convolutional neural networks to technical analysis by using technical indicator graphs, aiming to classify trading signals with potential high-profit. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究動機 1第二節 研究目的 3第三節 研究架構 4第二章 文獻探討 5第一節 技術指標 5第二節 深度學習結合金融市場應用 6第三節 卷積神經網路結合技術指標應用 7第四節 文獻回顧總結 7第三章 研究方法 8第一節 技術指標 8第二節 卷積神經網路發展 12第三節 卷積神經網路模型 14第四章 實證分析 20第一節 研究對象 20第二節 實驗架構 22第三節 實證結果 28第五章 結論與建議 37第一節 結論 37第二節 未來展望 38參考文獻 39附錄 41 zh_TW dc.format.extent 2882645 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107352006 en_US dc.subject (關鍵詞) 卷積神經網路 zh_TW dc.subject (關鍵詞) 深度學習 zh_TW dc.subject (關鍵詞) 技術分析 zh_TW dc.subject (關鍵詞) 技術指標 zh_TW dc.subject (關鍵詞) 黃金期貨 zh_TW dc.subject (關鍵詞) Convolutional Neural Network en_US dc.subject (關鍵詞) Deep Learning en_US dc.subject (關鍵詞) Technical Analysis en_US dc.subject (關鍵詞) Technical Index en_US dc.subject (關鍵詞) Gold Future en_US dc.title (題名) 卷積神經網路於黃金期貨技術指標投資之應用 zh_TW dc.title (題名) Application of Convolutional Neural Network on Gold Future Technical Index en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 一、中文文獻[1] 李杰穎. (2019). 卷積神經網路結合技術指標交易策略在台灣加權指數期貨之應用.[2] 劉昭雨，2017，卷積神經網路在金融技術指標之應用二、英文文獻[3] Malkiel, B. G., & Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), 383-417.[4] Brock, W., Lakonishok, J., & LeBaron, B. (1992). Simple technical trading rules and the stochastic properties of stock returns. The Journal of finance, 47(5), 1731-1764.[5] Pruitt, S. W., & White, R. E. (1988). The CRISMA Trading System: Who Says Technical Analysis Can`. Journal of Portfolio Management, 14(3), 55.[6] Tsai, C. F., & Wang, S. P. (2009, March). Stock price forecasting by hybrid machine learning techniques. In Proceedings of the international multiconference of engineers and computer scientists (Vol. 1, No. 755, p. 60).[7] Di Persio, L., & Honchar, O. (2016). Artificial neural networks architectures for stock price prediction: Comparisons and applications. International journal of circuits, systems and signal processing, 10(2016), 403-413.[8] Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2017, July). Forecasting stock prices from the limit order book using convolutional neural networks. In 2017 IEEE 19th Conference on Business Informatics (CBI) (Vol. 1, pp. 7-12). IEEE.[9] Pyo, S., Lee, J., Cha, M., & Jang, H. (2017). Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets. PloS one, 12(11).[10] Alexander, S. S. (1961). Price movements in speculative markets: Trends or random walks. Industrial Management Review (pre-1986), 2(2), 7. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202000508 en_US
