政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/143773

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/143773

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | 全文笔数/总笔数 : 111283/142199 (78%)
造访人次 : 48181837 在线人数 : 933

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

搜寻范围

查询小技巧：

您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果

若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据

进阶搜寻

主页 ‧ 登入 ‧ 上传 ‧ 说明 ‧ 关于政大典藏 ‧ 管理

到手机版

政大機構典藏 > 社會科學學院 > 經濟學系 > 學位論文 > Item 140.119/143773

请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/143773

题名:	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
作者:	蘇育正 Su, Yu-Cheng
贡献者:	蔡炎龍蕭明福 Thai, YenLung Shaw, MingFu 蘇育正 Su, Yu-Cheng
关键词:	深度學習強化學習深度強化學習虛擬貨幣投資組合 Reinforcement Learning Portfolio Crypto
日期:	2022
上传时间:	2023-03-09 18:23:05 (UTC+8)
摘要:	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。
參考文獻:	[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
描述:	碩士國立政治大學經濟學系 108258034
資料來源:	http://thesis.lib.nccu.edu.tw/record/#G0108258034
数据类型:	thesis
显示于类别:	[經濟學系] 學位論文

文件中的档案:

档案	描述	大小	格式	浏览次数
803401.pdf		1563Kb	Adobe PDF2	33	检视/开启

在政大典藏中所有的数据项都受到原著作权保护.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - 回馈