文化大學機構典藏 CCUR:Item 987654321/48804
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 47249/51115 (92%)
Visitors : 14252696      Online Users : 581
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: https://irlib.pccu.edu.tw/handle/987654321/48804


    Title: 整合GARCH建構類神經網路在台股指數期貨之預測
    Neural Network with GARCH Volatility for TAIEX Futures Prediction
    Authors: 藍柏超
    Contributors: 財務金融學系
    Keywords: 類神經網路
    台股指數期貨
    預測
    主成份分析
    GARCH波動度
    Date: 2020
    Issue Date: 2020-11-09 10:29:10 (UTC+8)
    Abstract: 台灣加權股價指數期貨,能夠提供了投資人作為避險的工具亦能作為投資商品來投資運用,即是提供投機者與套利者運用期貨之高槓桿的特性,以少許的資金去賺取巨額的報酬。台灣加權股價指數的變動容易受金融、經濟、政治、社會以及投資者心理等眾多因素的影響。故針對台灣加權股價指數期貨市場的一些特性,本文使用倒傳遞類神經網路作為台灣加權股價指數期貨之預測模型。運用該模型去預測隔日台股期貨收盤價格。本文採用價格、成交量、期貨到期時間差三大原始資料變數作為輸入變數,建構倒傳遞類神經網路,經由倒傳遞類神經模型訓練後,預測出台灣加權股價指數期貨隔日收盤指數。藉由尋找最適預測模型本實證首先搭配主成份分析對輸入變數進行降維,再進行整合GARCH波動,建構倒傳遞類神經網路預測模型,本研究實證結果發現,相較於原有倒傳遞類神經網路模型相比具有準確得預測能力。
    FITX futures provide investors to evade risks and serve as an investor commodity; in other words, speculators and arbitragers make use of the high-level feature of futures to earn enormous returns with a small sum of money. FITX price is easily influenced by various factors, including finance, economy, politics, society, and investors’ mind. In this study, some features of the FITX futures market and the back propagation network (BPN) are used to predict FITX futures. The BPN is adopted to predict the next-day closing prices of FITX futures. Firscly, the variables of the original data regarding price, quantity, and time, as well as the fluctuation estimated by GARCH, were taken as the input variables. The was used to establish the BPN. The next-day closing indices of FITX futures were predicted after training, as based on the back propagation model. In this empirical study, the principal component analysis is first used to reduce the dimensionality of the input variables, and then the GARCH fluctuation is integrated to construct an inverse transitive neural network prediction model. The empirical results of this study find that compared with the original inverse transitive neural network model Has the ability to predict accurately.
    Appears in Collections:[Department of Banking & Finance ] Thesis

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML174View/Open


    All items in CCUR are protected by copyright, with all rights reserved.


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