원문정보
초록
영어
The basic aim of this paper is to provide a model to explain stock performance paramount level. To reach this purpose, this research proposes that rough set theory (RS), allied with the use of Grey Prediction, Semi-Supervised Graph Regularized Non-negative Matrix Factorization (SGNMF), K-means and Grey Relation, can out-perform the more standard approaches that are employed in economics. This study focuses on stock to select the optimal stock portfolio out applying the financial statement datum from the New Taiwan Economy database (TEJ). Firstly, this study collects relative financial ratio datum as the conditional attributes selection and then uses GM(1,1) for forecasting, SGNMF for choosing the more important conditional attributes, and rough set for figuring the best portfolio out. Finally, the Grey relational analysis is used to reduce the investment risk for fund allocation. This study will demonstrate that rough sets model is applicable to stock portfolio. The empirical result in Taiwan: During five years (2009-2013), the average annual rate of return was 20.41%, the accumulated rate of return for 9 quarter was 61.22%. The portfolio determined by the model is a promising alternative to the conventional methods for economic and financial prediction..
목차
1. Introduction
2. Methodologies Review
2.1. Rough Sets
2.2. Grey Prediction Modeling(GM(1,1))
2.3. Semi-supervised Graph Regularized Non-negative Matrix Factorization(SGNMF)
2.4. Grey Relational Analysis
3. Research Model Development
3.1. Establishes Data Set for Rough Set By Grey Prediction Model
3.2. Decision-Making Attributes Selecting: Combining the Taiwan Industry Features with Buffet’s Rules
3.3. Modeling Flow of the Stock Portfolio Model
4. The Empirical Results of Stock Portfolio Model in Taiwan Stock Market
4.1. Material Reasoning
4.2. Difference of Fund Allocation and Their Investment Results
5. Conclusions and Discussions
Acknowledgements
References