跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 林為元
Lin, Wei-Yuan
論文名稱： 以類神經網路與區別分析模式研究證券風格之分類、辨識與投資績效
A study of equity style classification, identification and investment strategy with neural networks and discriminant analysis
指導教授： 蔡瑞煌
沈中華
學位類別： 碩士
Master
系所名稱： 商學院 - 資訊管理學系
Department of Management Information System
論文出版年： 1998
畢業學年度： 86
語文別： 英文
論文頁數： 51
中文關鍵詞： 人工類神經網路 、風格投資分析
外文關鍵詞： Artificial neural networks, Style analysis
相關次數： 點閱：157  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

    • 就目前所知，這是第一篇應用人工類神經網路在股票風格投資方面的研究。類神經網路在樣本內與樣本外的分類正確率皆優於區別分析，而且類神經網路在樣本內的訓練範例中達成了百分之百的分類正確率。此外，我們也解決了傳統方法無法展示股票風格動態的問題。

    檢視各種風格投資策略在台灣股票市場的績效表現之後，我們以神經網路為基礎，提出一個簡單而容易實行的投資策略。由這個策略的表現可以說明，即使在考慮了風險因素之後，積極的風格投資策略的確可以增加投資組合的績效表現。

    This is the first study of applying artificial neural networks (ANN) to classify and identify the equity styles. Regarding the accuracy, ANN outperforms discriminant analysis (DA) in all pure samples from 1987 to 1997. The ANN also commits the 100% classification accuracy for the in-sample training samples. In addition, the problem that traditional approach couldn't show equity style dynamics was solved with ANN and DA.

    The performances of style investing strategies were examined in Taiwan stock market. The proposed strategy is easily implemented by constructing portfolios based on the return, which neural networks forecasted. There is good evidence to show this simple strategy could enhance profit on the return and risk adjusted basis. This gives one evidence to illustrate that active style investing would add value.

    CHAPTER 1 INTRODUCTION-----1
    1.1 Background-----1
    1.2 Motive-----2
    1.3 Objectives

    CHAPTER 2 LITERATURE REVIEW-----4
    2.1 Growth and Value Styles-----4
    2.2 Neural Networks-----6
    2.2.1 The Back Propagation Neural Networks-----7
    2.2.2 RN's Learning Algorithm-----7
    2.2.3 The Learning Procedure ofRNBP-----12
    2.3 Discrimmant Analysis-----14
    2.3.1 Assumptions-----14
    2.3.2 Implementation-----15
    2.3.3 The Race between Neural Networks and Discriminant Analysis-----16

    CHAPTER 3 METHODOLOGY-----17
    3.1 Equity Style Classification and Identification-----17
    3.1.1 Classification Model Specification and Data-----17
    3.1.2 Classification Model Evaluation-----18
    3.1.3 Style Identification-----19
    3.2 Style Investing Strategies-----19
    3.3 Style Performance Indicators-----20

    CHAPTER 4 EMPIRICAL RESULT-----22
    4.1 Sty ie Classification-----22
    4.2 Style Identification-----22
    4.3 Equity Style Investing Performance-----24
    4.3.1 Benchmark Strategy - Single-Factor (P/E, P/B, P/S, and SGR)-----24
    4.3.2 Discriminant Score (SDA) and Neural Network Tendency (TNN) Strategies-----27
    4.3.3 Return-Oriented Style-Switching Strategy (ROSS)-----29

    CHAPTER 5 CONCLUSIONS AND FUTURE STUDY-----33
    5.1 Conclusions-----33
    5.2 Future Study-----33

    REFERENCE-----35

    APPENDIX

    APPENDIX 1 EQUITY STYLE IDENTIFICATION-----37
    APPENDIX 2 EQUITY STYLE INVESTING PERFORMANCE-----41
    APPENDIX 3 SENSITIVITY ANALYSIS WITH NEURAL NETWORKS-----48

    Figure

    Figure 2.1 The block diagram of RN's learning algorithm-----10
    Figure 2.2 The procedure of KNBP-----13
    Figure 3.1 The evaluation and identification procedure-----19
    Figure 4.1 Style tendencyofstock ll04-----23
    Figure 4.2 Style tendency of stock 1433-----23
    Figure 4.3 (a) Average quarterly returns (TNN and SDA)-----28
    Figure 4.3 (b) Standard deviation of quarterly returns (TNN and SDA)-----28
    Figure 4.3 (c) Risk adjusted returns (TNN and SDA)-----28

    Tables
    Table 2.1 The definition of the used notations-----8
    Table 2.2 Studies of Classification with ANN and DA-----16
    Table 3.1 Description of classification factors-----17
    Table 4.1 Misclassification rate of pure samples-----21
    Table 4.2 Returns and risk profile based on P/E, P/B, P/S, SGR-----25
    Panel A: Average quarterly returns (in Percent)-----25
    Panel B: Standard deviation of quarterly returns (in Percent)-----25
    Panel C: Risk adjusted returns (in Percent)-----25
    Table 4.3 Correlation coefficient matrix (P/E, P/B, P/S and SGR)-----26
    Table 4.4 Style returns and risk profile based on P/B and ROSS-----31
    Panel A: Average quarterly returns (in Percent)-----31
    Panel B: Standard deviation of quarterly returns (in Percent)-----31
    Panel C: Risk adjusted returns (in Percent)-----31
    Table 4.5 A Summary Performance of Style Investing Strategies-----32

    無法下載圖示 (限達賢圖書館四樓資訊教室A單機使用)
    QR CODE
    :::