| 研究生: |
蘇育正 Su, Yu-Cheng |
|---|---|
| 論文名稱: |
運用深度強化學習建立虛擬貨幣投資組合 Establish The Portfolio of Crypto Currency by Applying Deep-Reinforcement Learning |
| 指導教授: |
蔡炎龍
Thai, YenLung 蕭明福 Shaw, MingFu |
| 口試委員: |
蔡炎龍
Thai, YenLung 蕭明福 Shaw, MingFu 劉宣谷 Liu,Hsuan-Ku |
| 學位類別: |
碩士
Master |
| 系所名稱: |
社會科學學院 - 經濟學系 Department of Economics |
| 論文出版年: | 2022 |
| 畢業學年度: | 111 |
| 語文別: | 中文 |
| 論文頁數: | 30 |
| 中文關鍵詞: | 深度學習 、強化學習 、深度強化學習 、虛擬貨幣 、投資組合 |
| 外文關鍵詞: | Crypto |
| 相關次數: | 點閱:565 下載:0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本研究運用深度強化學習建立虛擬貨幣的投資組合,研究標的主要以 2021
年 12 月 31 日市值排名前 50 大的虛擬貨幣。研究期間從 2017 年 1 月 3 日至2021 年 12 月 31 日,並主要以五個因子(Factor):開盤價(Open)、最高價(High)、最低價(Low)、收盤價(Close)、成交量(Volume)為輸入資料(Input),並在一開始先以(1)市值、(2)平均振幅抓取 30 檔虛擬幣組建投資組合,輸入給深度強化學習模型進行訓練,最終發現相較於其他種因子建立的投資組合,平均振幅打造的投資組合表現更好,也比單一持續持有比特幣來的更合適。
誌謝..................................................... 1
摘要..................................................... 2
目錄..................................................... 3
表目錄 .................................................. 5
圖目錄 .................................................. 6
第一章 緒論 ............................................. 7
第一節 研究動機 ..................................... 7
第二節 研究目的 ..................................... 8
第三節 研究架構與問題設定 ........................... 9
第二章 文獻回顧 ......................................... 11
第一節 虛擬貨幣市場的資產配置 ...................... 11
第二節 強化學習在投資上的應用 ...................... 12
第三章 研究設計 ......................................... 13
第一節 強化學習模型概述 ............................ 13
第二節 深度強化學習與模型設定 ...................... 14
第四章 資料來源及實證結果 ............................... 21
第一節 資料來源與說明 .............................. 21
第二節 模型設定 .................................... 22
第三節 實證結果 .................................... 23
第五章 結論與未來展望 ................................... 28
參考文獻 ................................................ 29
[1] Fan Fang, Carmine Ventre, Michail Basios, Leslie Kanthan, DavidMartinez-Rego, Fan Wu and Lingbo Li. Cryptocurrency trading: a comprehensive survey. Finanical Innovation,8(13),2022.
[2] Timothy King and Dimitrios Koutmos. Herding and feedback trading in cryptocurrency markets. Annals of Operations Research,300:79-97,2021.
[3] WeiSun, Alisher Tohirovich, Dedahanov, Ho YoungShin and Wei PingLi. Factors affecting institutional investors to add cryptocurrency to asset portfolios. The North American Journal of Economics and Finance,volume 58,2021.
[4] Paraskevi Katsiampa, Larisa Yarovaya and DamianZięba. Highfrequency connectedness between Bitcoin and other top-traded crypto assets during the COVID-19 crisis. Journal of International Financial Markets, Institutions and Money,volume 79,2022.
[5] Andrés Arévalo, Jaime Niño, G. Hernández and Javier Sandoval. High-Frequency Trading Strategy Based on Deep Neural Networks.International Conference on intelligent Computing, LNAI,volume 9773,2016.
[6] Maria Čuljak,BojanTomić and SašaŽiković . Benefits of sectoral cryptocurrency portfolio optimization. Research in International Business and Finance,volume 60,2022.
[7] Golnoosh Babaei,Paolo Giudici and EmanuelaRaffinetti. Explainable artificial intelligence for crypto asset allocation. Finance Research Letters,volume 47,Part B,2022.
[8] Leonardo Kanashiro Felizardo,Francisco CaioLima Paiva,Catharinede Vita Graves,Elia Yathie Matsumoto,Anna Helena Reali Costa,Emilio DelMoral-Hernandez and Paolo Brandimarte. Outperforming algorithmic trading reinforcement learning systems: A supervised approach to the 30
cryptocurrency market. Expert Systems with Applications,volume 202,2022.
[10] Hongfeng Xu,Lei Chai,Zhiming Luo and Shaozi Li. Stock movement prediction via gated recurrent unit network based on reinforcement learning with incorporated attention mechanisms. Neurocomputing,volume 467,Pages 214-228,2022.
[11] Fengrui Liu,Yang Li,Baitong Li,Jiaxin Li and Huiyang Xie . Bitcoin transaction strategy construction based on deep reinforcement learning. Applied Soft Computing,volume113,Part B,2021.
[12] Thibaut Théate and Damien Ernst . An application of deep reinforcement learning to algorithmic trading. Expert Systems with Applications,volume 173,2021.
[13] Liguo Weng,Xudong Sun,Min Xia,Jia Liu and Yiqing Xu. Portfolio Trading System of Digital Currencies: A Deep Reinforcement Learning with Multidimensional Attention Gating Mechanism. Neurocomputing,volume 402,Pages 171-182,2019
全文公開日期 2028/02/21