TITLE:
Stock Selection Based on a Hybrid Quantitative Method
AUTHORS:
Lichun Tang, Qimin Lin
KEYWORDS:
Random Forest, Selection of Financial Characteristic, Quantum Genetic Algorithm, Support Vector Regression, Quantitative Stock Selection
JOURNAL NAME:
Open Journal of Statistics,
Vol.6 No.2,
April
27,
2016
ABSTRACT: Quantitative stock selection has become a research hotspot in the
field of investment decision. As the data mining technology becomes mature,
quantitative stock selection has made great progress. From the perspective of
value investment, this paper selects top 200 stocks of A share in terms of
market value. With the random forest (RF), financial characteristic variables
with significant impact on SVR are screened out. At the same time with quantum
genetic algorithm (QGA) superior to the traditional genetic algorithm (GA), SVR
parameters are deeply and dynamically sought for, so as to build the RF-QGA-SVR
model for year-to-year stock ranking. The quantitative stock selection model is
built, and the empirical analysis of its stock selection performance is
conducted. The conclusion is as follows: 1) Optimizing SVR with QGA has higher
precision than the traditional genetic algorithm, and is more excellent than
the traditional GA optimization; 2) SVR after RF optimization of characteristic
variables more significantly improves the accuracy of stock ranking and
prediction; 3) In the stock ranking obtained from the RF-QGA-SVR model, the
yields of top stock portfolios are much higher than the market benchmark yield.
At the same time, the yields of the top 10 stock portfolios are the highest,
and the top 30 stock portfolios are the most stable. This study has positive
reference significance on quantitative stock selection in the field of
quantitative investment.