English  |  正體中文  |  简体中文  |  Items with full text/Total items : 52355/87459 (60%)
Visitors : 9128475      Online Users : 236
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU 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://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/107693

    Title: 運用SVR與Bass模型於台灣主機板與筆記型電腦預測分析
    Authors: 蕭裕耀
    Keywords: 預測;貝氏擴散模式;支持向量回歸;非線性最小平分法;基因演算法;粒子群最佳化;Forecasting;bass diffusion model;support vector regression;non-linear least square;genetic algorithm;particle swarm optimization
    Date: 2013-06-01
    Issue Date: 2016-10-12 02:11:58 (UTC+8)
    Publisher: 國立臺灣科技大學管理研究所
    Abstract: 台灣是世界排名第一的主機板與筆記型電腦生產國家, 其在2011的佔有率分別為80.4% 與93.6%.而其未來之預測發展對高階主管而言是非常重要. 本研究目的即是提供有效預測模式給主機板,筆記型電腦製造商與相關產業作為未來擴產與投資之重要參考. 在本研究中, 我們運用支持向量回歸與貝氏擴散模式, 分析1998年至2012年台灣主機板與筆記型電腦季出貨之資料, 運用格子點參數搜尋,非線性最小平分法, 基因演算法與粒子群最佳化,分別找出支持向量回歸與貝氏擴散模式之最佳參數. 而運用平均絕對值百分比誤差(Mean Absolute Percentage Error, 簡稱MAPE)進行預測效益評估.本研究結果分析,支持向量回歸之平均絕對值百分比誤差低於貝氏擴散模式,可運用在主機板與筆記型電腦市場預測分析。

    Taiwan is the world’s leading motherboard (MB) and notebook (NB) manufacturer, boasting a 2011 global market share of 80.4% and 93.6%, respectively. It is highly crucial for executives to predict future trends from within an environment of uncertainty. The aim of this study is to provide an efficient forecasting model to serve as a key reference for MB and NB manufacturers looking to expand or invest. We propose the following 2 forecasting models based on MB and NB quarterly shipment data from 1998-2012: (a) support vector regression (SVR) using a grid search method for the estimation of three parameters; and (b) Bass diffusion models (BDMs) using non-linear least square (NLS), genetic algorithm (GA), and particle swarm optimization (PSO) methods for parameter optimization. We also evaluate the forecasting accuracy by actual mean absolute percentage error (MAPE).The obtained MAPE values indicate that the proposed SVR model outperforms the BDMs using NLS, GA, and PSO for fitting and forecasting based on MAPE, and is therefore recommended for MB and NB market forecasting analysis.
    Appears in Collections:[化學工程與材料工程學系暨研究所] 專書

    Files in This Item:

    File SizeFormat

    All items in 機構典藏 are protected by copyright, with all rights reserved.

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