請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95650完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張智星 | zh_TW |
| dc.contributor.advisor | Jyh-Shing Jang | en |
| dc.contributor.author | 劉薇 | zh_TW |
| dc.contributor.author | Wei Liu | en |
| dc.date.accessioned | 2024-09-15T16:30:21Z | - |
| dc.date.available | 2024-09-16 | - |
| dc.date.copyright | 2024-09-14 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-12 | - |
| dc.identifier.citation | [1] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
[2] Qingnan Sun, Marko V Jankovic, Lia Bally, and Stavroula G Mougiakakou. Predicting blood glucose with an lstm and bi-lstm based deep neural network. In 2018 14th symposium on neural networks and applications (NEUREL), pages 1–5. IEEE, 2018. [3] Zhicheng Wang, Biwei Huang, Shikui Tu, Kun Zhang, and Lei Xu. Deeptrader: a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 643–650, 2021. [4] Harry Markowitz. Portfolio selection. The Journal of Finance, 7(1):77–91, 1952. [5] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013. [6] Yue Deng, Feng Bao, Youyong Kong, Zhiquan Ren, and Qionghai Dai. Deep direct reinforcement learning for financial signal representation and trading. IEEE transactions on neural networks and learning systems, 28(3):653–664, 2016. [7] John Moody, Matthew Saffell, Yuansong Liao, and Lizhong Wu. Reinforcement learning for trading systems and portfolios: Immediate vs future rewards. In Decision Technologies for Computational Finance: Proceedings of the fifth International Conference Computational Finance, pages 129–140. Springer, 1998. [8] Financial Times. Jpmorgan develops robot to execute trades, 2017. Accessed: 2024-08-06. [9] PYMNTS. Ai explained: Reinforcement learning and how it shapes commerce, 2024. Accessed: 2024-08-06. [10] Zhengyao Jiang, Dixing Xu, and Jinjun Liang. A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059, 2017. [11] Jingyuan Wang, Yang Zhang, Ke Tang, Junjie Wu, and Zhang Xiong. Alphastock: A buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1900–1908, 2019. [12] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017. [13] Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and Wancai Zhang. Informer: Beyond efficient transformer for long sequence time series forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 11106–11115, 2021. [14] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [15] Yingmei Chen, Zhongyu Wei, and Xuanjing Huang. Incorporating corporation relationship via graph convolutional neural networks for stock price prediction. In Proceedings of the 27th ACM international conference on information and knowledge management, pages 1655–1658, 2018. [16] Sheng Xiang, Dawei Cheng, Chencheng Shang, Ying Zhang, and Yuqi Liang. Temporal and heterogeneous graph neural network for financial time series prediction. In Proceedings of the 31st ACM international conference on information & knowledge management, pages 3584–3593, 2022. [17] Kaijian He, Qian Yang, Lei Ji, Jingcheng Pan, and Yingchao Zou. Financial time series forecasting with the deep learning ensemble model. Mathematics, 11(4):1054, 2023. [18] Khaled A Althelaya, El-Sayed M El-Alfy, and Salahadin Mohammed. Stock market forecast using multivariate analysis with bidirectional and stacked (lstm, gru). In 2018 21st Saudi Computer Society National Computer Conference (NCC), pages 1–7. IEEE, 2018. [19] Omer Berat Sezer, Mehmet Ugur Gudelek, and Ahmet Murat Ozbayoglu. Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied soft computing, 90:106181, 2020. [20] Xiao-Yang Liu, Zhuoran Xiong, Shan Zhong, Hongyang Yang, and Anwar Walid. Practical deep reinforcement learning approach for stock trading. arXiv preprint arXiv:1811.07522, 2018. [21] Xiao-Yang Liu, Hongyang Yang, Qian Chen, Runjia Zhang, Liuqing Yang, Bowen Xiao, and Christina Dan Wang. FinRL: A deep reinforcement learning library for automated stock trading in quantitative finance. arXiv preprint arXiv:2011.09607, 2020. [22] Musonda Katongo and Ritabrata Bhattacharyya. The use of deep reinforcement learning in tactical asset allocation. Available at SSRN 3812609, 2021. [23] Damian Kisiel and Denise Gorse. Portfolio transformer for attention-based asset allocation. In International Conference on Artificial Intelligence and Soft Computing, pages 61–71. Springer, 2022. [24] Xiaokang Hu. Stock price prediction based on temporal fusion transformer. In 2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), pages 60–66. IEEE, 2021. [25] Zura Kakushadze. 101 formulaic alphas. Wilmott, 2016(84):72–81, 2016. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95650 | - |
| dc.description.abstract | 本研究探討在動態且複雜的金融市場中優化投資組合策略的挑戰。傳統方法如Markowitz均值-方差模型，由於其靜態性和對歷史數據的依賴，在實際應用中往往效果不佳。深度強化學習（Deep Reinforcement Learning）模型，特別是DeepTrader，已顯示出適應市場變化的潛力。然而，這些模型在應用於不同市場（如台灣市場）時，往往會出現極端表現變化的問題。本研究旨在通過整合Transformer網絡來改進DeepTrader模型，替換其原始模型中的Graph Convolutional Network和Long Short-Term Memory部分。Transformer網絡因其優越的長期依賴關係捕捉能力和對股票間複雜關聯的處理能力而被選中。我們在美國和台灣市場上測試了所提出的改進模型，以評估其性能和穩定性。具體實驗包括在美國市場上運用DeepTrader模型，深入分析其在不同市場條件下的行為和性能表現，並比較DeepTrader模型在台灣市場上的表現，識別其在長期關聯學習中的不足之處。此外，我們測試改進後的Transformer模型，評估其在穩定性和適應不同市場環境方面的提升。研究結果表明，改進後的模型在處理市場波動和適應不同市場環境方面顯著優於原始DeepTrader模型，特別是在應對市場變化和捕捉長期依賴關係方面顯示出更強的能力。每月更新權重又可以將改進後的Transformer模型效果發揮得更好，使其在動態市場環境中保持更高的穩定性和準確性。 | zh_TW |
| dc.description.abstract | This research addresses the challenges of optimizing portfolio strategies in dynamic financial markets. Traditional methods like the Markowitz mean-variance model often fail due to their static nature. Deep reinforcement learning (DRL) models, particularly DeepTrader, show promise but struggle with performance variability across different markets, such as Taiwan. We aim to enhance DeepTrader by integrating Transformer networks, replacing the Graph Convolutional Network and Long Short-Term Memory components. Transformers were chosen for their ability to capture long-term dependencies and handle complex stock relationships. We tested the improved model in both U.S. and Taiwanese markets. Key findings include analyzing DeepTrader's behavior in the U.S. market under various conditions, identifying performance issues in the Taiwanese market related to long-term correlation learning, and demonstrating that the Transformer-based model improves stability and adaptability across different markets. The improved model significantly outperforms the original DeepTrader in handling market volatility and adapting to diverse market environments, showing stronger capabilities in capturing long-term dependencies and responding to market changes. Additionally, implementing monthly updates to the model's weights further enhances the performance of the Transformer-based model, ensuring greater stability and accuracy in dynamic market environments. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-15T16:30:20Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-15T16:30:21Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements iii
摘要 v Abstract vii Contents ix List of Figures xiii List of Tables xv Chapter 1 Introduction . . . . . . . . . . . . . . . . . . . . . 1 1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Research Problem . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Research Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.4 Research Contributions . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.5 Chapter Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 Chapter 2 Related Work . . . . . . . . . . . . . . . . . . . . . 7 2.1 Graph Convolutional Network . . . . . . . . . . . . . . . . . . . . . 7 2.2 Long Short-Term Memory . . . . . . . . . . . . . . . . . . . . . . . 8 2.3 Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . 9 2.4 Transformer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 Chapter 3 Method . . . . . . . . . . . . . . . . . . . . . 15 3.1 Optimization Based on DeepTrader . . . . . . . . . . . . . . . . . . 15 3.2 Transformer-based Attention . . . . . . . . . . . . . . . . . . . . . . 18 3.2.1 Enhancements with Transformer Models . . . . . . . . . . . . . . . 18 3.2.2 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.2.2.1 Asset Scoring Unit (ASU) . . . . . . . . . . . . . . . . 20 3.2.2.2 Market Scoring Unit (MSU) . . . . . . . . . . . . . . . 21 3.2.2.3 Portfolio Generator . . . . . . . . . . . . . . . . . . . 22 Chapter 4 Experimental Setup . . . . . . . . . . . . . . . . . . . . . 25 4.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.1.1 US Market . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.1.2 TW Market . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.2 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 4.3 Environment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.4 Parameter Settings . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.5 Roadmap of Experiments . . . . . . . . . . . . . . . . . . . . . . . . 30 4.5.1 Experiment 1: Analysis of Market and ρ Interaction . . . . . . . . . 30 4.5.2 Experiment 2: Test in the Taiwanese Market . . . . . . . . . . . . . 31 4.5.3 Experiment 3: Improvements Based on Transformer . . . . . . . . . 33 4.5.4 Experiment 4: Model Retraining with Updated Information . . . . . 34 Chapter 5 Experiments and Results . . . . . . . . . . . . . . . . . . . . . 37 5.1 Experiment 1: Analysis of Market and ρ Interaction . . . . . . . . . 38 5.1.1 Training, Validation and Test Intervals . . . . . . . . . . . . . . . . 39 5.1.2 Performance Metrics and Observations . . . . . . . . . . . . . . . . 39 5.1.3 Comparative Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 41 5.1.4 Discussion and Implications . . . . . . . . . . . . . . . . . . . . . 43 5.2 Experiment 2: Test in the Taiwanese Market . . . . . . . . . . . . . 44 5.2.1 Training, Validation and Test Intervals . . . . . . . . . . . . . . . . 47 5.2.2 Performance Metrics and Observations . . . . . . . . . . . . . . . . 47 5.2.3 Comparative Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 49 5.2.4 Discussion and Implications . . . . . . . . . . . . . . . . . . . . . 51 5.3 Experiment 3: Improvements Based on Transformer . . . . . . . . . 52 5.3.1 Training, Validation, and Test Intervals . . . . . . . . . . . . . . . . 52 5.3.2 Performance Metrics and Observations . . . . . . . . . . . . . . . . 53 5.3.3 Comparative Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 54 5.3.4 Discussion and Implications . . . . . . . . . . . . . . . . . . . . . 57 5.4 Experiment 4: Model Retraining with Updated Information . . . . . 58 5.4.1 Training, Validation, and Test Intervals of Exp4 . . . . . . . . . . . 59 5.4.2 Performance Metrics and Observations . . . . . . . . . . . . . . . . 61 5.4.3 Comparative Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 62 5.4.4 Discussion and Implications . . . . . . . . . . . . . . . . . . . . . 64 Chapter 6 Conclusions and Future Directions . . . . . . . . . . . . . . . . . . 67 6.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67 6.2 Future Research Directions . . . . . . . . . . . . . . . . . . . . . . . 69 References . . . . . . . . . . . . . . . . . . . . . 71 | - |
| dc.language.iso | en | - |
| dc.title | 基於深度強化學習將動態市場條件納入投資組合最佳化 | zh_TW |
| dc.title | Incorporating Dynamic Market Conditions into Portfolio Optimization via Deep Reinforcement Learning | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.coadvisor | 蔡政安 | zh_TW |
| dc.contributor.coadvisor | Chen-An Tsai | en |
| dc.contributor.oralexamcommittee | 陳永耀;韓傳祥 | zh_TW |
| dc.contributor.oralexamcommittee | Yung-Yaw Chen;Chuan-Hsiang Han | en |
| dc.subject.keyword | 投資組合優化,深度強化式學習,Transformer, | zh_TW |
| dc.subject.keyword | Portfolio optimization,Deep reinforcement learning,Transformer, | en |
| dc.relation.page | 74 | - |
| dc.identifier.doi | 10.6342/NTU202403155 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-08-14 | - |
| dc.contributor.author-college | 共同教育中心 | - |
| dc.contributor.author-dept | 統計碩士學位學程 | - |
| 顯示於系所單位： | 統計碩士學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf | 5.21 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。