跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/19 08:29
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:楊榮駿
研究生(外文):YANG,JUNG-CHUN
論文名稱:基於LSTM預測模型的股票分析比較:以元大寶來台灣卓越50指數股票型基金為例
論文名稱(外文):Stock Analysis and Comparison Based on LSTM Prediction Model: Taking Yuanta Bora Taiwan Excellence 50 Index Stock Fund as an Example
指導教授:蕭瑛東蕭瑛東引用關係
指導教授(外文):HSIAO,YING-TUNG
口試委員:郭政謙許佳興
口試委員(外文):KUO,CHENG-CHIENSHEU,JIA-SHING
口試日期:2022-06-21
學位類別:碩士
校院名稱:國立臺北教育大學
系所名稱:資訊科學系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:31
中文關鍵詞:股價預測深度學習長短期記憶時間序列
外文關鍵詞:stock price forecastingdeep learninglong short-term memorytime series
相關次數:
  • 被引用被引用:3
  • 點閱點閱:568
  • 評分評分:
  • 下載下載:183
  • 收藏至我的研究室書目清單書目收藏:1
股價預測在社會上一直是個主流的話題,同時也是具有很大挑戰性的研究題目,投資者總是試圖實時監控風險,以便預先得知市場趨勢走向,以獲得更高的投資回報,然而預測有助於保護買賣雙方之間的證券交易以及降低所涉及的風險。本文將使用長短期記憶演算法來進行股價預測,並以元大寶來台灣卓越50指數股票型基金為主要的預測目標,有許多技術派的交易者會透過五日均線、二十日均線來策略來進行交易的進出準則,故將嘗試三個預測模組,分別是利用五天資料預測未來一天開盤價漲跌幅趨勢、十天資料預測未來一天開盤價漲跌幅趨勢以及二十天資料預測未來一天開盤價漲跌幅趨勢,並使用均方根誤差來評估比較模型。研究結果顯示預測結果會有偏移的現象,預測數據會比實際數據晚個幾天。
Stock price forecasting has always been a mainstream topic in society, and it is also a very challenging research topic. Investors always try to monitor risks in real time in order to understand market movements in advance and thus obtain higher investment returns. Helps protect securities transactions between buyers and sellers and reduce the risks involved. This article will use the long-term and short-term memory algorithm to predict the stock price, with the Yuanta Bora Taiwan Boutique 50 Index Stock Fund as the main forecast target. Many technical traders will use the 5-day moving average and the 20-day moving average for forecasting, so we will try three forecasting modules, namely using the five-day data to predict the trend of the opening price of the next day, and the ten-day data to predict the opening price trend of the next day. 20 days of data. Predict the opening price trend for the next day and use the root mean square error to evaluate the comparison model. The results of the study showed that the forecast results were skewed, with the forecast data being several days behind the actual data.
1. 緒論 1
1.1研究動機與目的 1
1.2 研究方法 2
1.3 論文架構 2
2. 文獻回顧 3
2.1 股價預測方法 3
2.2 ETF(股票型指數基金)簡介 5
2.3 元大寶來台灣卓越50指數股票型基金介紹 6
2.4 人工智慧的發展 8
2.5 深度學習 9
2.6 Tensorflow 10
2.7 Keras 11
2.8 遞迴神經網路(RNN) 11
2.9 長短記憶模型(LSTM) 13
2.10 均方根誤差(MSE) 15
2.11 梯度下降法(Adam) 16
3.研究方法 17
3.1 資料來源與描述 17
3.2 研究架構 17
3.3 資料準備 18
3.4 模型建構 19
4. 實驗結果與分析 21
4.1 五天資料預測未來一天開盤價漲跌幅 21
4.2 十天資料預測未來一天開盤價漲跌幅 22
4.3 二十天資料預測未來一天開盤價漲跌幅 24
4.4 LSTM模型調整 25
4.5 實驗結果比較 26
5. 結論與未來研究方向 28
5.1 結論 28
5.2 未來研究方向 28
參考文獻 29

[1]M. R. Hassan, B. Nath and M. Kirley, "A fusion model of HMM ANN and GA for stock market forecasting," Expert Syst. Appl., vol. 33, no. 1, pp. 171-180, Jul. 2007.
[2]W. Huang, Y. Nakamori and S.Y. Wang, "Forecasting stock market movement direction with support vector machine", Comput. Oper. Res., vol. 32, no. 10, pp. 2513-2522, Oct. 2005.
[3]J. Sun and H. Li, "Financial distress prediction using support vector machines: Ensemble vs. Individual," Appl. Soft Comput., vol. 12, no. 8, pp. 2254-2265, Aug. 2012.
[4]P. Ou and H. Wang, "Prediction of stock market index movement by ten data mining techniques," Modern Appl. Sci., vol. 3, no. 12, pp. 28-42, Nov. 2009.
[5]F. Liu and J. Wang, "Fluctuation prediction of stock market index by legendre neural network with random time strength function," Neurocomputing, vol. 83, pp. 12-21, Apr. 2012.
[6]C.F. Tsai, Y. C. Lin, D. C. Yen and Y. M. Chen, "Predicting stock returns by classifier ensembles," Appl. Soft Comput., vol. 11, no. 2, pp. 2452-2459, Mar. 2011.
[7]R. D. A. Araäjo and T. A. E. Ferreira, "A Morphological-Rank-Linear evolutionary method for stock market prediction," Inf. Sci., vol. 237, pp. 3-17, Jul. 2013.
[8]M. Ballings, D. Van den Poel, N. Hespeels and R. Gryp, "Evaluating multiple classifiers for stock price direction prediction," Expert Syst. Appl., vol. 42, no. 20, pp. 7046-7056, Nov. 2015.
[9]S. Basak, S. Kar, S. Saha, L. Khaidem and S. R. Dey, "Predicting the direction of stock market prices using tree-based classifiers," North Amer. J. Econ. Finance, vol. 47, pp. 552-567, Jan. 2019.
[10]B. Weng, W. Martinez, Y. T. Tsai, C. Li, L. Lu, J. R. Barth, et al., "Macroeconomic indicators alone can predict the monthly closing price of major U.S. indices: Insights from artificial intelligence time-series analysis and hybrid models," Appl. Soft Comput., vol. 71, pp. 685-697, Oct. 2018.
[11]台灣證卷交易所,https://www.twse.com.tw/zh/page/ETF/intro.html#01 ,2022/03/31瀏覽
[12]A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj and A. Iosifidis, "Forecasting stock prices from the limit order book using convolutional neural networks," Proc. IEEE 19th Conf. Bus. Informat. (CBI), pp. 10-15, Jul. 2017.
[13]S. Selvin, R. Vinayakumar, E. A. Gopalakrishnan, V. K. Menon and K. P. Soman, "Stock price prediction using LSTM RNN and CNN-sliding window model," Proc. Int. Conf. Adv. Comput. Commun. Informat. (ICACCI), pp. 234-239, Sep. 2017.
[14]C. Qi, S. Huang and X. Wang, "Monitoring water quality parameters of taihu lake based on remote sensing images and LSTM-RNN," IEEE Access, vol. 8, pp. 188068-188081,2020.
[15]T. Li, M. Hua and X. Wu, "A hybrid CNN-LSTM model for forecasting particulate matter (PM2.5)," IEEE Access, vol. 8, pp. 26933-26940, Feb,2020.
[16]N. T. A. S. N. Sima Siami-Namini, "The performance of LSTM and bi LSTM in forecasting time series," IEEE International Conference on Big Data, p. 8, 2019.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊