跳到主要內容

臺灣博碩士論文加值系統

(44.192.94.177) 您好!臺灣時間:2024/07/21 22:21
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:賴俊元
研究生(外文):LAI, CHUN-YUAN
論文名稱:基於長短期記憶之股票買賣預測推薦
論文名稱(外文):The Stock Trading Predicts Recommendations Based on Long Short-Term Memory Neural Network
指導教授:陳榮靜陳榮靜引用關係
指導教授(外文):CHEN, RUNG-CHING
口試委員:王清德林春宏陳榮靜陳靖國
口試委員(外文):WANG,CHING-TELIN, CHUEN-HORNGCHEN, RUNG-CHINGCHEN, JEANG-KUO
口試日期:2021-01-15
學位類別:碩士
校院名稱:朝陽科技大學
系所名稱:資訊管理系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2021
畢業學年度:109
語文別:中文
論文頁數:46
中文關鍵詞:股票預測股票技術指標長短期記憶
外文關鍵詞:Stock predictTechnical IndicatorLong Short-term Memory.
相關次數:
  • 被引用被引用:4
  • 點閱點閱:322
  • 評分評分:
  • 下載下載:101
  • 收藏至我的研究室書目清單書目收藏:0
隨著技術不斷地變化、資訊科技進步,大數據分析的研究已經廣泛應用於多個領域,不論是健康照護、交通、製造、教育、金融等,大數據既龐大且複雜,且擁有非常大的價值。股票是一種有價證券,也是股份公司為了籌集資金發給投資人的憑證。簡單來說,股票投資就是擁有那家公司部分的所有權,有福同享,有難同當;當公司賺錢時,就能依照持股比例分配盈餘,反之,也得承受股票投資虧損的風險。關於股票分析的研究文獻已經有相當的數量,投資者在投資股票之前有兩種類型的分析,基本面分析以及技術分析。前者是以股票的內在價值、行業和經濟的表現、政治氣候為判斷方式,後者則是以通過研究股市產生的統計數據評估股票[1]。
本研究透過臺灣證卷交易所蒐集之每日數據,以台灣50、鴻海、台泥、台積電、台塑、廣達股票為例,使用開盤價(Open price)、最低價(Low price)、最高價(High price)、成交量(Volume)以及收盤價(Close price)作為輸入資料,藉由神經網路長短期記憶 (Long Short-term Memory, LSTM) 來訓練股票預測模型,預測未來股票動向,並用均絕對誤差 (Mean-Absolute Error, MAE)、均方根誤差 (或稱方均根偏移、均方根差、方均根差等,Root-Mean-Square Deviation、Root-Mean-Square Error、RMSD、RMSE) 作評估,再將預測結果以常用的技術性指標隨機指標 (Stochastic Oscillator, KD)、相對強弱指標 (Relative Strength Index, RSI)、指數平滑異同移動平均線 (Moving Average Convergence / Divergence, MACD) 以及能量潮指標 (On Balance Volume, OBV) 來判斷該股票適合買進、賣出或是繼續持有。透過對模型預測實驗結果的準確性評估,接著使用技術性指標來判斷該時間點適不適合進場該股票,輕鬆做到股票投資。

As technology and information technology advances, research on big data analytics has been widely used in many fields, whether it is health care, transportation, manufacturing, education, finance, etc. Big data is both broad and complex, and its knowledge is a considerable value. Stock is a kind of securities, which is a certificate issued by a stock company to investors to raise funds. The stock investment is part of the ownership of the company. When the company makes money, it can distribute the surplus according to the shareholding ratio, and vice versa;, it also has to bear the risk of stock investment losses. There is already a considerable amount of research literature on stock analysis, and investors have two types of analysis, fundamental analysis, and technical analysis, before investing in stocks.
This study used the daily data collected by the Taiwan Stock Exchange that took Taiwan 50 companies. The companies are Foxconn, Taiwan Cement Corp., Taiwan Semiconductor Manufacturing Company, Formosa Petrochemical Corporation, and Quanta Computer Inc. stocks. The system used the values of open price, low price, high price, volume, and close price as input data. The data are used to train stock forecasting models by Neural Network Long Short-term Memory (LSTM) to predict future stock trends. Then, Use Mean-Absolute Error (MAE), Root Mean Square Error (RMSE) to do the evaluation. The commonly used technical indicators Stochastic Oscillator (KD), Relative Strength Index (RSI), Moving Average Convergence Divergence (MACD) and energy tide indicators ( On Balance Volume, OBV) to determine whether the stock condition. The conditions include suitable for buying, selling, or continuing to hold by evaluating the accuracy of the model prediction experiment results, and then using technical indicators to determine whether the time point is suitable for entering the stock to achieve stock investment.

摘要 ...................................................................I
Abstract .........................................................III
致謝 ..................................................................IV
目錄 ..................................................................VI
表目錄 ................................................................VIII
圖目錄 ..................................................................IX
第一章 導論 ...........................................................1
1.1研究背景 ...........................................................1
1.2研究動機 ...........................................................3
1.3研究目的 ...........................................................4
1.4論文架構 ...........................................................6
第二章 文獻探討 ...........................................................7
2.1股票預測相關文獻 ...................................................7
2.2技術指標 ..........................................................10
2.2.1隨機指標 (Stochastic Oscillator, KD) ..........................11
2.2.2相對強弱指標 (Relative Strength Index, RSI) ..........................13
2.2.3指數平滑異同移動平均線 (Moving Average Convergence / Divergence, MACD) ..........................................................................14
2.2.4能量潮指標 (On Balance Volume, OBV) ..................................16
第三章 研究方法 ..........................................................17
3.1系統架構 ..........................................................17
3.2長短期記憶(Long Short-term Memory, LSTM) ..........................20
3.3丟棄法(Dropout) ..................................................26
3.4 正規化及反正規化(Normalization and Denormalization) ..................26
3.5 Rectified Linear Unit (Relu)層 ..................................27
3.6全連結層(Fully Connected Layer) ..................................28
3.7優化器(Optimizer) ..................................................28
2.8 損失函數(Lose Function) ..........................................29
第四章 實驗與結果 ..................................................30
4.1測試資料說明與實驗 ..................................................30
4.2實驗結果 ..........................................................36
第五章 結論與未來展望 ..................................................42

表 1 時間框架示例 ..................................................19
表 2長短期記憶遞歸神經網路之模型參數整理 ..................................25
表 3臺灣50基金成分股 ..................................................31
表 4原始資料示例 ..........................................................34
表 5正規化後資料示例 ..................................................35
表 6模型誤差評估 ..........................................................36
表 7預測結果之技術指標買賣評估 ..........................................39
表 8 正確答案之技術指標買賣評估 ..........................................40

圖 1 KD指標買賣點 ..................................................11
圖 2 MACD指標買賣點 ..................................................14
圖 3 OBV指標買賣點 ..................................................16
圖 4模型訓練預測及技術指標評估流程 ..........................................18
圖 5誤差計算流程 ..........................................................18
圖 6 LSTM模型架構 ..................................................19
圖 7 Sigmoid激活函數 ..................................................22
圖 8 LSTM模型架構圖 ..................................................23
圖 9 ReLU激活函數 ..................................................27
圖 10 全連結層示意圖 ..................................................28
圖 11資料期間的股價變化 ..................................................32
圖 12各公司以每日為輸入預測與測試對比之結果 ..................................37
圖 13 各公司以每週為輸入預測與測試對比之結果 ..........................38



[1]謝劍平(2012),投資學-基本原理與實務,智勝文化事業有限公司,第5。
[2]王昭平、金鐵英、吳訂宜(2007) ,「台股之弱式效率市場檢定」,高苑學報,第十三卷,第191-220頁。
[3]黃偉倫、劉長遠 (2017)。一種股市預測獲利行情的深度模型:以台灣股市為例,博士論文,國立臺灣大學資訊工程學研究所,臺北。
[4]黃柏華、陳俊男 (2018)。機器學習應用於技術分析指標的探討-以台灣五十成分股為例,碩士論文,國立臺灣科技大學財務金融研究所,臺北。
[5]法意研究部,法意教你Y!選股獲利秘技,法意資產管理股份有限公司,2012,第12頁。
[6]元大投信,http://www.yuantaetfs.com/#/FundWeights/1066
[7]Ou, Jane A., and Stephen H. Penman, “Financial statement analysis and the prediction of stock returns. Journal of accounting and economics,” 1989, Vol.11(4), pp.295-329.
[8] Agrawal, J. G., V. Chourasia, and A. Mittra, “State-of-the-art in stock prediction techniques,” International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 2013, Vol.2(4), pp.1360-1366..
[9] Holthausen, Robert W., and David F. Larcker, “The prediction of stock returns using financial statement information. Journal of accounting and economics,” 1992, Vol.15(2-3), pp.373-411.
[10] Ding, Xiao, Zhang, Yue, Liu, Ting, and Duan, Junwen, “Deep learning for event-driven stock prediction,” In Twenty-fourth International Joint Conference on Artificial Intelligence, 2015.
[11] Kim, Kyoung-jae, and Ingoo Han, “Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index,” Expert systems with Applications, 2000, Vol.19(2), pp.125-132.
[12] Chen, Kai, Yi Zhou, and Fangyan Dai, “A LSTM-based method for stock returns prediction: A case study of China stock market,” In 2015 IEEE international conference on big data, 2015, pp. 2823-2824, IEEE.
[13] Rather, Akhter Mohiuddin, Arun Agarwal, and V. N. Sastry, “Recurrent neural network and a hybrid model for prediction of stock returns,” Expert Systems with Applications, 2015, Vol.42(6), pp.3234-3241.
[14] Kaboudan, Mark A., “Genetic programming prediction of stock prices,” Computational Economics, 2000, Vol.16(3), pp.207-236.
[15] Akita, Ryo, Yoshihara, Akira, Matsubara, Takashi, and Uehara, Kuniaki, “Deep learning for stock prediction using numerical and textual information,” In 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), 2016, pp. 1-6, IEEE.
[16] Boyacioglu, Melek Acar, and Derya Avci, “An adaptive network-based fuzzy inference system (ANFIS) for the prediction of stock market return: the case of the Istanbul stock exchange,” Expert Systems with Applications, 2010, Vol.37(12), pp.7908-7912.
[17] Schöneburg, Eberhard, “Stock price prediction using neural networks: A project report,” Neurocomputing, 1990, Vol.2(1), pp.17-27.
[18]Patel, Jigar, Shah, Sahil, Thakkar, Priyank and Kotecha, K, “Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques,” Expert Systems with Applications, 2015, Vol. 42(1), pp. 259-268.
[19] Murtaza Roondiwala, Harshal Patel, and Shraddha Varma, “Predicting Stock Prices Using LSTM,” International Journal of Science and Research, 2015, Vol. 6(4), pp.1754-1756.
[20] Wu, George Guan-Ru, Tony Chieh-Tse Hou, and Jin-Lung Lin, “Can economic news predict Taiwan stock market returns?,” Asia Pacific Management Review, 2018, Vol. 24(1), pp.54-59.
[21] Hochreiter, Sepp, and Jürgen Schmidhuber, “Long Short-Term Memory,” Neural Computation, 1997, Vol. 9(8), pp. 1735-1780.
[22] Lipton Zachary C., Kale David C., Elkan Charles, and Wetzel Randall, “Learning to diagnose with LSTM recurrent neural networks, “ International Conference on Learning Representations, 2016.
[23] Grover, Aditya, Ashish Kapoor, and Eric Horvitz, “A Deep Hybrid Model for Weather Forecasting,” 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015, pp. 379-386.
[24] Caraka, Rezzy Eko, Bakar, Sakhinah Abu, Tahmid, Muhammad, Yasin, Hasbi, and Kurniawan, Isma Dwi, “Neurocomputing Fundamental Climate Analysis,” TELKOMNIKA Indonesian Journal of Electrical Engineering, 2019, Vol. 17(4), pp. 1818-1827.
[25]Ghaderi, Amir, Borhan M. Sanandaji, and Faezeh Ghaderi, “Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting,” arXiv preprint arXiv:1707.08110, 2017.
[26]Qiu, Xueheng, Ren, Ye, Suganthan, Ponnuthurai Nagaratnam, and Amaratunga, Gehan A.J., “Empirical Mode Decomposition based ensemble deep learning for load demand time series forecasting,” Appl. Soft Comput., 2017, Vol. 54, pp. 246-255.
[27]Caraka, Rezzy Eko, and Sakhinah Abu Bakar, “Evaluation Performance of Hybrid Localized Multi Kernel SVR (LMKSVR) In Electrical Load Data Using 4 Different Optimizations,” J. Eng. Appl. Sci., 2018, Vol. 13(17), pp. 75-79.
[28]Phan, NhatHai, Wang, Yue, Wu, Xintao, and Dou, Dejing, “Differential Privacy Preservation for Deep Auto-Encoders: An Application of Human Behavior Prediction,” 30th AAAI Conference on Artificial Intelligence, 2016, Vol. 16, pp. 1309-1316.
[29]Laptev, Nikplay, Yosinski, Jason, Li, Li Erran, and Smyl, Slawek, “Time-series Extreme Event Forecasting with Neural Networks at Uber,” International Conference on Machine Learning Time Series Workshop, 2017.
[30]Toharudin, Toni, Caraka, Rezzy Eko, Bachrudin, Achmad, Bakar, Sakhinah Abu, and Ambarsari, Dewi, “Copula-Based Feedforward Neural Network Genetic Algorithm Cargo Forecasting,” International Journal of Advances in Soft Computing and its Applications, 2019, Vol. 11(1), pp. 22-33.
[31]Tian, Yan, Zhang, Kaili, Li, Jianyuan, Lin, Xianxuan, and Yang, Bailin, “LSTM-based Traffic Flow Prediction with Missing Data,” Neurocomputing, 2018, Vol. 318 , pp. 297-305.
[32]Atsalakis, George S., and Kimon P. Valavanis, “Surveying stock market forecasting techniques - Part II: Soft computing methods,” Expert Systems with Applications, 2009, Vol.36(3), pp. 5932-5941.
[33]https://school.stockcharts.com/doku.php?id=technical_indicators:stochastic_oscillator_fast_slow_and_full

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