Research On Quantitative Strategy Based On Multi-factor Stock Selection And Hidden Markov Model Timing

Quantitative trading has been a hot topic in China in recent years.It has been developed overseas for more than 40 years and is now becoming more mature.Researchers have been working hard to find more stable and profitable trading strategies.An excellent trading strategy can comprehensively consider the market,allocate investors' assets more accurately,grasp investment opportunities more accurately and obtain higher returns.Quantitative investment strategies usually need to examine two important dimensions: "stock selection" and "timing".Combining these two dimensions can not only reduce investment risks and obtain stable returns,but also promote the healthy and stable operation of the entire stock market.This article discusses the establishment of a quantitative strategy based on hidden Markov model timing and multi-factor stock selection to control investor risk and obtain better returns.More factors can choose a quantitative strategy section factor stock selection model is introduced,and then based on the optimal mining factors libraries and other quantitative factor library used by the selected factor platform,data preprocessing,and then using IC series of single factor test,through correlation analysis,with the final selected eight factors more factor stock selection model is established.According to the established multi-factor strategy,20 stocks were selected as alternative stocks.The part of time-calculation strategy construction in this paper takes csi 300 index as the research object,and the sample research interval is November 3,2014,solstice,January 23,2020,including bull market,bear market and volatile market.By calling the kaiyuan data interface,relevant eigenvalues are obtained and calculated as the observation vectors of the HMM,and the hidden Markov model is parametric trained to identify and predict the index state and make buy or sell operations.From the perspective of strategy results,on the premise of controllable risk,the selected investment standard achieved excess returns,and the withdrawal and volatility were well controlled.Finally,combining the time-calculation strategy and stock selection strategy,the time-calculation strategy is implemented for the selected high-quality stocks,and the results are weighted and compared with a single strategy.In addition,two representative stocks were selected for in-depth analysis.By comparing the effects of multi-factor stock selection models,time-calculation strategies and portfolio strategies to test the feasibility and effectiveness of time-calculation strategies based on HMM and multi-factor quantitative stock selection based on valuation methods.Can combined strategies achieve higher investment income? In the course of the study,we examined the advantages and disadvantages of various strategies and,in combination with the findings,prepared relevant recommendations for investors.