臺灣人文及社會科學引文索引資料庫系統

:::

詳目顯示

回上一頁
第 1 筆 / 總合 1 筆   第一頁 上一頁 下一頁 最後一頁
/1頁
題名：基於卷積神經網路的市場結構圖像方法建構交易策略
作者：朱陳彬
作者(外文)：Ju, Chern-Bin
校院名稱：國立陽明交通大學
系所名稱：資訊管理研究所
指導教授：陳安斌
學位類別：博士
出版日期：2022
主題關鍵詞：卷積神經網路；金融時間序列預測；市場輪廓理論；市場結構圖；交易策略；時間因果；價格變化趨勢分類；Convolutional neural network；Financial time series forecasting；Market Profile；Structure of market activities image；Trading Strategies；Temporal causality；Price movement classification
原始連結：連回原系統網址new window
相關次數：
  • 被引用次數被引用次數:期刊(0) 博士論文(0) 專書(0) 專書論文(0)
  • 排除自我引用排除自我引用:0
  • 共同引用共同引用:0
  • 點閱點閱:3
本研究嘗試以人工智慧中深度學習方法，卷積神經網路建立趨勢分類模型，辨識市場趨勢延續或反轉的行為，以此建構順勢與逆勢交易策略，嘗試建構出能在市場中投資獲利的策略。
文獻指出，大部分的深度學習研究使用遞歸神經網路系列的模型進行金融時間序列預測，然而，這些研究大部分皆以原始的時間序列資料作為模型的輸入，市場中存在著交易目的不同參與者，如投機、避險或套利等，因為他們的交易週期不同，原始時間序列資料中容易潛藏著許多影響模型學習的雜訊。為了避免在建立模型學習過多的雜訊，本研究提出市場結構圖像，先以市場輪廓理論為基礎，將金融時間序列資料中的交易活動轉換成市場輪廓結構，這種結構易於發現趨勢主導者的行為。此外，考量金融市場為一動態環境，特徵值發生的先後順序也應視為造成趨勢變化的一個因果，為了使模型能學習特徵值的時間因果關係，在轉換結構圖形的過程中，將以不同的灰階值呈現不同時間發生的市場交易活動。本研究共設計5種灰階市場結構圖像，不同的圖像將關注不同時間週期的市場活動。為避免人工介入進行特徵工程，本研究利用卷積神經網路訓練趨勢變化分類模型，此網路能於圖像卷積的過程，自動萃取圖像中與金融市場趨勢變化的相關的重要的特徵值。
考量不同投資人具有不同的交易風格、風險偏好與本金，本研究根據訓練後的趨勢變化分類模型，建構了順勢交易策略及逆勢交易策略，並加入部位管理與風險管理方法，以美國標普500 E-mini期貨進行實證研究。研究結果顯示，以具時間因果特徵值之灰階市場結構圖像，訓練卷積神經網路模型，能發現趨勢延續或反轉的行為，建構出的順勢交易策略其獲利能力與風險表現皆能顯著優於較不具時間因果的圖像以及隨機交易模型。
This study attempted to identify the trend continuation or reversal behavior using deep learning method, convolutional neural network (CNN), to build a trend classification model, and developed trading strategies that could make profits in the financial market.
Literature indicated that most deep learning studies used recurrent neural network and its variants for financial time series prediction due to their internal memory cell that could process incoming input with the previous states. However, most of the research used the raw time series data as learning features. There were many participants with diverse trading timeframe in the market. In addition, they had distinct purposes such as arbitraging, hedging, or speculating, resulting in plenty of noise in the raw time series data. To solve this problem, we proposed the structure of market activities image which converted financial time series into bell-shape representation based on Market Profile theory so that the majority activities of trend dominators could be detected. Furthermore, considering the financial market is dynamic, the order of occurrence of the feature in the structure image should also be considered as a cause and effect of the trend changes. Therefore, five types of grayscale structure image were designed, focusing on distinct timeframe of market participants. To learn important features in structure image related to financial market trend changes, this study employed the CNN that could extract features automatically during the convolutional process.
The experimental results of momentum trading based on model demonstrated statistically significant differences in profitability and risk performance and indicated CNN trained with proposed grayscale structure image could applied for discovering trend continuation or reversal behavior and development of trading strategies.
[1] J. P. Steidlmayer, Markets and Market Logic, Chicago, Porcupine Press, 1984.
[2] C.-C. Lin, C.-S. Chen, and A.-P. Chen, "Using intelligent computing and data stream mining for behavioral finance associated with market profile and financial physics," Applied Soft Computing, vol. 68, pp. 756-764, 2018.
[3] C.-C. Chen, Y.-C. Kuo, C.-H. Huang, and A.-P. Chen, "Applying market profile theory to forecast Taiwan Index Futures market," Expert Systems with Applications, vol. 41, no. 10, pp. 4617-4624, 2014.
[4] R. L. Galvez, A. A. Bandala, E. P. Dadios, R. R. P. Vicerra, and J. M. Z. Maningo, "Object detection using convolutional neural networks," in TENCON 2018-2018 IEEE Region 10 Conference, 2018: IEEE, pp. 2023-2027.
[5] E. Hoseinzade and S. Haratizadeh, "CNNpred: CNN-based stock market prediction using a diverse set of variables," Expert Systems with Applications, vol. 129, pp. 273-285, 2019.
[6] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature, vol. 521, no. 7553, pp. 436-444, 2015.
[7] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[8] Y. LeCun, K. Kavukcuoglu, and C. Farabet, "Convolutional networks and applications in vision," in Proceedings of 2010 IEEE international symposium on circuits and systems, 2010: IEEE, pp. 253-256.
[9] D. C. Ciresan, U. Meier, J. Masci, L. M. Gambardella, and J. Schmidhuber, "Flexible, high performance convolutional neural networks for image classification," in Twenty-second international joint conference on artificial intelligence, 2011.
[10] O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, "Financial time series forecasting with deep learning: A systematic literature review: 2005–2019," Applied soft computing, vol. 90, p. 106181, 2020.
[11] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[12] H. Maqsood et al., "A local and global event sentiment based efficient stock exchange forecasting using deep learning," International Journal of Information Management, vol. 50, pp. 432-451, 2020.
[13] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, 2012.
[14] A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and L. Fei-Fei, "Large-scale video classification with convolutional neural networks," in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2014, pp. 1725-1732.
[15] O. B. Sezer and A. M. Ozbayoglu, "Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach," Applied Soft Computing, vol. 70, pp. 525-538, 2018.
[16] L. Deng and D. Yu, "Deep learning: methods and applications," Foundations and trends® in signal processing, vol. 7, no. 3–4, pp. 197-387, 2014.
[17] J. L. Elman, "Finding structure in time," Cognitive science, vol. 14, no. 2, pp. 179-211, 1990.
[18] M. I. Jordan, "Serial order: A parallel distributed processing approach," in Advances in psychology, vol. 121: Elsevier, 1997, pp. 471-495.
[19] M. Sundermeyer, R. Schlüter, and H. Ney, "LSTM neural networks for language modeling," in Thirteenth annual conference of the international speech communication association, 2012.
[20] K. Chen, Y. Zhou, and F. Dai, "A LSTM-based method for stock returns prediction: A case study of China stock market," in 2015 IEEE international conference on big data (big data), 2015: IEEE, pp. 2823-2824.
[21] M. Hiransha, E. A. Gopalakrishnan, V. K. Menon, and K. Soman, "NSE stock market prediction using deep-learning models," Procedia computer science, vol. 132, pp. 1351-1362, 2018.
[22] K. Khare, O. Darekar, P. Gupta, and V. Attar, "Short term stock price prediction using deep learning," in 2017 2nd IEEE international conference on recent trends in electronics, information & communication technology (RTEICT), 2017: IEEE, pp. 482-486.
[23] X. Zhang and Y. Tan, "Deep stock ranker: A LSTM neural network model for stock selection," in International conference on data mining and big data, 2018: Springer, pp. 614-623.
[24] J. F. Dalton, E. T. Jones., Robert, R. B. Dalton, Mind Over Markets: Power Trading with Market Generated Information, 2nd ed. Traders Press, 1999.
[25] Robert Rhea, The Dow Theory, Barron’s, 1932.
[26] B. Penfold, The Universal Tactics of Successful Trend Trading: Finding Opportunity in Uncertainty, 1st ed. Wiley, 2020.
[27] J. Magee, R. D. Edwards and W.H.C. Bassetti, Technical Analysis of Stock Trends, 9th ed, New York, AMACOM, 2018.
[28] J. E. Granville, New key to stock market profits. PrenticeHall, 1963.
[29] M. M. Kumbure, C. Lohrmann, P. Luukka, and J. Porras, "Machine learning techniques and data for stock market forecasting: a literature review," Expert Systems with Applications, p. 116659, 2022.
[30] J. Welles Wilder, New Concepts in Technical Trading Systems, TREND RESEARCH, 1978.
[31] I. K. Nti, A. F. Adekoya, and B. A. Weyori, "A systematic review of fundamental and technical analysis of stock market predictions," Artificial Intelligence Review, vol. 53, no. 4, pp. 3007-3057, 2020.
[32] Q. Cao, K. B. Leggio, and M. J. Schniederjans, "A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market," Computers & Operations Research, vol. 32, no. 10, pp. 2499-2512, 2005.
[33] S. T. A. Niaki and S. Hoseinzade, "Forecasting S&P 500 index using artificial neural networks and design of experiments," Journal of Industrial Engineering International, vol. 9, no. 1, pp. 1-9, 2013.
[34] Z. Rustam and P. Kintandani, "Application of support vector regression in indonesian stock price prediction with feature selection using particle swarm optimisation," Modelling and Simulation in Engineering, vol. 2019, 2019.
[35] J. Zhang et al., "Can the exchange rate be used to predict the shanghai composite index?," IEEE Access, vol. 8, pp. 2188-2199, 2019.
[36] W. F. Sharpe, "The sharpe ratio," Streetwise–the Best of the Journal of Portfolio Management, pp. 169-185, 1998.
[37] J. M.-T. Wu, S.-H. Lin, J.-H. Syu, and M.-E. Wu, "Embedded draw-down constraint reward function for deep reinforcement learning," Applied Soft Computing, vol. 125, p. 109150, 2022.
[38] E. F. Fama, "Efficient capital markets: A review of theory and empirical work," The journal of Finance, vol. 25, no. 2, pp. 383-417, 1970.
[39] E. F. Fama, "Random walks in stock market prices," Financial analysts journal, vol. 51, no. 1, pp. 75-80, 1995.
[40] 黃閔淞，「應用自組織映射神經網路進行公司動態財務行為之體質檢定」，國立交通大學，資訊管理研究所碩士論文，2008年。
[41] 王志鈞，笑笑看線圖：跟著六大名師學技術分析，早安財經文化有限公司，2010年。
[42] 林茂昌，我的職業是股東，早安財經文化有限公司，2018年。
[43] 查欣瑜，「法人籌碼對台股未來走勢影響之研究」，國立交通大學，財務金融研究所碩士論文，2011年。
[44] 郭怡君，「應用市場輪廓於台指期市場行為發現之研究」，國立交通大學，資訊管理所碩士論文，2012年。
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
QR Code
QRCODE

臺灣人文及社會科學引文索引資料庫

目前上線人數：1459（臺灣：1441，外國：18） ／ 本年度總使用人次：2488187 ／ 訪客人次（自102年09月）：68304961
國家圖書館著作權聲明 Copyright © 2013 All rights reserved.
本館地址: 100201臺北市中山南路20號． 本館地圖及交通資訊．
總機：(02)23619132．最佳瀏覽解析度為1024x768以上