請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86629完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 呂育道(Yuh-Dauh Lyuu) | |
| dc.contributor.author | Han-Yu Chen | en |
| dc.contributor.author | 陳涵宇 | zh_TW |
| dc.date.accessioned | 2023-03-20T00:07:34Z | - |
| dc.date.copyright | 2022-08-10 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-05 | |
| dc.identifier.citation | [1] B. Babcock, M. Datar, and R. Motwani, “Sampling from a moving window over streaming data,” in 2002 Annual ACM-SIAM Symposium on Discrete Algorithms, 2001, pp. 633–634. [2] R. Bardenet and B. Kégl, “Surrogating the surrogate: accelerating Gaussian-process-based global optimization with a mixture cross-entropy algorithm,” in 27th International Conference on Machine Learning, 2010, pp. 55–62. [3] J. Benediktsson. “TA-Lib.” https://github.com/mrjbq7/ta-lib (accessed May 13, 2022). [4] Y. Bengio, “Gradient-based optimization of hyperparameters,” Neural Computation, vol. 12, no. 8, pp. 1889–1900, 2000. [5] J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization,” Journal of Machine Learning Research, vol. 13, no. 2, pp. 281–305, 2012. [6] F. Black, “Noise,” Journal of Finance, vol. 41, no. 3, pp. 528–543, 1986. [7] G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: Forecasting and control. John Wiley & Sons, 2015. [8] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [9] J. Cao, Z. Li, and J. Li, “Financial time series forecasting model based on CEEMDAN and LSTM,” Physica A: Statistical Mechanics and Its Applications, vol. 519, pp. 127–139, 2019. [10] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794. [11] K. Cho, B. Van Merriënboer, D. Bahdanau, and Y. Bengio, “On the properties of neural machine translation: Encoder-decoder approaches,” arXiv preprint arXiv:1409.1259, 2014. [12] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995. [13] T. G. Dietterich, “Ensemble methods in machine learning,” in International Workshop on Multiple Classifier Systems, 2000, pp. 1–15. [14] E. F. Fama, “Efficient capital markets: A review of theory and empirical work,” Journal of Finance, vol. 25, no. 2, pp. 383–417, 1970. [15] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, vol. 55, no. 1, pp. 119–139, 1997. [16] C. L. Giles, S. Lawrence, and A. C. Tsoi, “Noisy time series prediction using recurrent neural networks and grammatical inference,” Machine Learning, vol. 44, no. 1, pp. 161–183, 2001. [17] I. Goodfellow et al., “Generative adversarial nets,” Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680, 2014. [18] S. Hochreiter, Y. Bengio, P. Frasconi, and J. Schmidhuber, “Gradient flow in recurrent nets: the difficulty of learning long-term dependencies,” in A field guide to dynamical recurrent neural networks. Piscataway, NJ: Wiley-IEEE Press, 2001, pp. 237–243. [19] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [20] T. Hsieh, H. Hsiao, and W. Yeh, “Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm,” Applied Soft Computing, vol. 11, no. 2, pp. 2510–2525, 2011. [21] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and practice. Melbourne: OTexts, 2018. [22] N. Jegadeesh and S. Titman, “Returns to buying winners and selling losers: Implications for stock market efficiency,” Journal of Finance, vol. 48, no. 1, pp. 65–91, 1993. [23] K. Kim, “Financial time series forecasting using support vector machines,” Neurocomputing, vol. 55, no. 1–2, pp. 307–319, 2003. [24] B. F. King, “Market and industry factors in stock price behavior,” Journal of Business, vol. 39, no. 1, pp. 139–190, 1966. [25] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014. [26] M. Kraus and S. Feuerriegel, “Decision support from financial disclosures with deep neural networks and transfer learning,” Decision Support Systems, vol. 104, pp. 38–48, 2017. [27] Y. LeCun et al., “Backpropagation applied to handwritten zip code recognition,” Neural Computation, vol. 1, no. 4, pp. 541–551, 1989. [28] A. W. Lo and A. C. MacKinlay, “Stock market prices do not follow random walks: Evidence from a simple specification test,” Review of Financial Studies, vol. 1, no. 1, pp. 41–66, 1988. [29] S. M. Lundberg and S. Lee, “A unified approach to interpreting model predictions,” Advances in Neural Information Processing Systems, vol. 30, pp. 4768–4777, 2017. [30] R. T. Marler and J. S. Arora, “Survey of multi-objective optimization methods for engineering,” Structural and Multidisciplinary Optimization, vol. 26, no. 6, pp. 369–395, 2004. [31] J. Močkus, “On Bayesian methods for seeking the extremum,” in Optimization Techniques IFIP Technical Conference, 1975, pp. 400–404. [32] J. Moody, “Economic forecasting: Challenges and neural network solutions,” in Proceedings of the International Symposium on Artificial Neural Networks, 1995, pp. 789–800. [33] T. Nguyen and S. Yoon, “A novel approach to short-term stock price movement prediction using transfer learning,” Applied Sciences, vol. 9, no. 22, 2019, Art no. 4745. [34] P. Pai and C. Lin, “A hybrid ARIMA and support vector machines model in stock price forecasting,” Omega, vol. 33, no. 6, pp. 497–505, 2005. [35] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, 1986. [36] J. Sola and J. Sevilla, “Importance of input data normalization for the application of neural networks to complex industrial problems,” IEEE Transactions on Nuclear Science, vol. 44, no. 3, pp. 1464–1468, 1997. [37] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014. [38] M. Stone, “Cross‐validatory choice and assessment of statistical predictions,” Journal of the Royal Statistical Society: Series B (Methodological), vol. 36, no. 2, pp. 111–133, 1974. [39] J. L. Ticknor, “A Bayesian regularized artificial neural network for stock market forecasting,” Expert Systems with Applications, vol. 40, no. 14, pp. 5501–5506, 2013. [40] L. Torrey and J. Shavlik, “Transfer learning,” in Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques. Hershey, PA: IGI global, 2010, pp. 242–264. [41] R. Ye and Q. Dai, “A novel transfer learning framework for time series forecasting,” Knowledge-Based Systems, vol. 156, pp. 74–99, 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86629 | - |
| dc.description.abstract | 深度學習近年來被廣泛地應用於多個領域，但是使用深度學習時需要較為大量的訓練資料，因此若想將深度學習應用於對新上市的股票進行股價預測必須解決資料量不足的問題。 遷移學習常被用於處理訓練資料不足的問題，但在金融領域中較常用於文本分析，部分對於市場指數或股價漲跌趨勢預測的研究又缺少使用遷移學習前後的模型表現比較，因此無法說明遷移學習在金融領域中對於模型表現的影響。本論文以台股為對象，嘗試以不同實驗觀察遷移學習是否能緩解新上市股票資料不足的問題。根據本論文的實驗結果，遷移學習普遍而言可以提升對新上市股票的股價預測表現，但部分結果也說明並非選擇任何股票作為模型預訓練的資料在遷移學習上都能有好表現，因此需謹慎選擇。 | zh_TW |
| dc.description.abstract | Although deep learning has been widely applied in many fields recently, it needs plenty of training data, thus it is difficult to apply to stock price prediction for newly listed companies due to lack of historical data. Transfer learning is a common technique to deal with the problem of scarcity of data. But in financial domain, it is often applied to textual analysis. Some studies on market index or stock trend prediction that apply transfer learning do not compare the performances with and without transfer learning, making the net effects of transfer learning hard to isolate. In this thesis, we design experiments to track the effects of transfer learning on model performances in Taiwan stock market. The results reveal that transfer learning can generally raise the performance on predicting prices of newly listed stocks, but some special cases also demonstrate that which stock is used for model pre-training before applying transfer learning has significant impacts on the performance. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-20T00:07:34Z (GMT). No. of bitstreams: 1 U0001-0308202220241200.pdf: 1580311 bytes, checksum: 193967f816f42851b625932c8c0d4d96 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 口試委員會審定書 i 誌謝 ii 摘要 iii Abstract iv 目錄 v 圖目錄 vii 表目錄 viii 第一章 緒論 1 1.1 簡介 1 1.2 論文架構 3 第二章 背景 4 2.1 股價預測 4 2.1.1 效率市場假說 4 2.1.2 以深度學習預測股價 5 2.2 類神經網路 6 2.2.1 前饋神經網路 6 2.2.2 遞迴類神經網路 7 2.2.3 長短期記憶模型 8 2.3 遷移學習 10 第三章 實驗方法 11 3.1 實驗設計 11 3.2 資料來源及處理 13 3.3 訓練與驗證資料 13 3.4 超參數選擇 14 第四章 實驗結果 17 4.1 實驗一 17 4.2 實驗二 19 4.2.1 電子類股 19 4.2.2 金融類股 20 4.2.3 航運類股 22 4.3 實驗三 23 4.3.1 電子類股 23 4.3.2 金融類股 24 4.3.3 航運類股 24 第五章 結論與建議 25 5.1 結論 25 5.2 未來展望 26 參考文獻 27 圖2.1、神經元示意圖 6 圖2.2、RNN示意圖與步驟展開圖 7 圖2.3、LSTM架構示意圖 9 圖2.4、遷移學習的三種可能改善方向 10 圖3.1、移動式視窗運作原理 14 圖3.2、放棄法的簡單示意圖 15 圖3.3、損失隨訓練輪數的變化 16 圖4.1、長榮歷史收盤價走勢 18 圖4.2、長榮航歷史收盤價走勢 18 圖4.3、中華電歷史收盤價走勢 20 圖4.4、國泰金歷史收盤價走勢 21 圖4.5、上海商銀歷史收盤價走勢 21 圖4.6、台灣高鐵歷史收盤價走勢 22 表3.1、各類股中來源資料的選股 11 表3.2、各類股中目標資料的選股 12 表3.3、實驗使用之超參數 16 表4.1、各股票直接訓練後的模型MAPE（單位：%） 17 表4.2、電子類股不同訓練方式的模型MAPE比較（單位：%） 20 表4.3、金融類股不同訓練方式的模型MAPE比較（單位：%） 21 表4.4、航運類股不同訓練方式的模型MAPE比較（單位：%） 22 表4.5、電子類股的模型最終表現MAPE比較（單位：%） 23 表4.6、金融類股的模型最終表現MAPE比較（單位：%） 24 表4.7、航運類股的模型最終表現MAPE比較（單位：%） 24 | |
| dc.language.iso | zh-TW | |
| dc.subject | 股價預測 | zh_TW |
| dc.subject | 遞迴類神經網路 | zh_TW |
| dc.subject | 長短期記憶模型 | zh_TW |
| dc.subject | 台灣證券市場 | zh_TW |
| dc.subject | 長短期記憶模型 | zh_TW |
| dc.subject | 遷移學習 | zh_TW |
| dc.subject | 台灣證券市場 | zh_TW |
| dc.subject | 股價預測 | zh_TW |
| dc.subject | 遞迴類神經網路 | zh_TW |
| dc.subject | 遷移學習 | zh_TW |
| dc.subject | Stock price prediction | en |
| dc.subject | Recurrent neural network | en |
| dc.subject | Long short-term memory | en |
| dc.subject | Recurrent neural network | en |
| dc.subject | Stock price prediction | en |
| dc.subject | Taiwan stock market | en |
| dc.subject | Transfer learning | en |
| dc.subject | Long short-term memory | en |
| dc.subject | Taiwan stock market | en |
| dc.subject | Transfer learning | en |
| dc.title | 遷移學習對股價預測的影響：以台股為例 | zh_TW |
| dc.title | Evaluation of Transfer Learning on Stock Price Prediction in the Taiwan Stock Market | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陸裕豪(U-Hou Lok),張經略(Ching-Lueh Chang),金國興(Gow-Hsing King) | |
| dc.subject.keyword | 遷移學習,長短期記憶模型,遞迴類神經網路,股價預測,台灣證券市場, | zh_TW |
| dc.subject.keyword | Transfer learning,Long short-term memory,Recurrent neural network,Stock price prediction,Taiwan stock market, | en |
| dc.relation.page | 31 | |
| dc.identifier.doi | 10.6342/NTU202202030 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2022-08-05 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-08-10 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0308202220241200.pdf | 1.54 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。