English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 97106/127750 (76%)
Visitors : 33247562      Online Users : 287
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/131007


    Title: 利用深度學習模型建構基金最適資產配置
    Using Deep Learning Model to Construct The Optimal Asset Allocation In Mutual Fund
    Authors: 黃勝彥
    Huang, Sheng-Yan
    Contributors: 黃泓智
    Huang, Hong-Chih
    黃勝彥
    Huang, Sheng-Yan
    Keywords: 基金分群
    長短期記憶模型
    波動度控制
    最適化權重
    Mutual fund
    LSTM
    Volatility control
    Optimal asset allocation
    Date: 2020
    Issue Date: 2020-08-03 17:41:33 (UTC+8)
    Abstract: 本研究主要是以長短期記憶模型(LSTM)進行基金報酬率預測,搭配波動度控制的方法,建構穩健的投資組合。為了達成風險分散的目的,本論文將股票型基金與債券型基金分別處理,其中,股票型基金劃分為六大市場,包含日本、美國、新興市場、歐洲、亞太不含日本與台灣,而債券型基金劃分為三大類別,包含投資級別債券、高收益債券以及新興市場債券,於資產配置時,從各大地區與類別挑選出預期表現較佳之基金,達成風險分散之目的。在波動度控制的部分,本文以下方標準差做為波動度的衡量,並嘗試以固定波動度與變動波動度的方法進行資產配置,最終比較其結果之差異。實證結果發現,透過每月檢視投資組合的風險,變動波動度控制能夠迅速反應市場狀況,且較為保守,整體績效優於固定波動度控制。
    The purpose of this study is to use LSTM model to predict the return of mutual fund, and build a stable portfolio. In order to achieve the purpose of risk diversification, this study treats bond fund and stock fund separately. Moreover, stock funds are divided into six major markets, and bond funds are divided into three major categories. The final portfolio will include funds from each category in order to diversify the risk. This study uses two volatility control methods to determine the asset allocation, including fixed volatility control and variable volatility control. The empirical results find that through monthly review of portfolio risk, variable volatility control method can quickly reflect market conditions, and therefore the overall performance is better than fixed volatility control.
    Reference: 1.Abe Masaya and Nakayama Hideki(2018).“Deep learning for forecasting stock returns in the cross-section,” Pacific-Asia Conference on Knowledge Discovery and Data Mining. 273-284.

    2.Minh Dang Lien, Sadeghi-Niaraki Abolghasem, Huy Huynh Duc, Min Kyungbok and Moon Hyeonjoon(2018). “Deep learning approach for short-term stock trends prediction based on two-stream gated recurrent unit network,” IEEE Access, 55392-55404.

    3.A.Connel and M.Hodgson(2017). “Managing investment outcomes with volatility control.”

    4.Nelson David MQ., Pereira Adriano C.M. and de Oliveira Renato A.(2017). “Stock market's price movement prediction with LSTM neural networks,” 2017 International joint conference on neural networks (IJCNN), 1419-1426.

    5.Xiong Ruoxuan, Nichols Eric P. and Shen Yuan(2017). “Deep learning stock volatility with google domestic trends.”

    6.Chong Eunsuk, Han Chulwoo, and Park Frank C(2017).“Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies,” Expert Systems with Applications, 187-205.

    7.Roondiwala Murtaza, Patel Harshal and Varma Shraddha(2017). “Predicting stock prices using LSTM,” International Journal of Science and Research (IJSR), 1754-1756.

    8.Hansson Magnus(2017).“On stock return prediction with LSTM networks.”

    9.Keller Wouter J., Butler Adam and Kipnis Ilya(2015).“ Momentum and Markowitz: a golden combination.”

    10.Harry M. Markowitz(2010). “Portfolio theory: as I still see it,” Annu. Rev. Financ. Econ, 1-23.

    11.Hochreiter Sepp and Schmidhuber Jürgen(1997). “Long short-term memory,” Neural computation, 1735-1780.

    12.Kimoto Takashi, Asakawa Kazuo, Yoda Morio and Takeok Masakazu(1990). “Stock market prediction system with modular neural networks,” 1990 IJCNN international joint conference on neural networks, 1-6.

    13.Levy Haim and Sarnat Marshall(1970). “International diversification of investment portfolios,” The American Economic Review, 668-675.

    14.Grubel, Herbert G.(1968). “Internationally diversified portfolios: welfare gains and capital flows,” The American Economic Review, 1299-1314.
    Description: 碩士
    國立政治大學
    風險管理與保險學系
    107358012
    Source URI: http://thesis.lib.nccu.edu.tw/record/#G0107358012
    Data Type: thesis
    DOI: 10.6814/NCCU202000778
    Appears in Collections:[風險管理與保險學系 ] 學位論文

    Files in This Item:

    There are no files associated with this item.



    All items in 政大典藏 are protected by copyright, with all rights reserved.


    社群 sharing

    著作權政策宣告
    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。
    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。
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback