Stock selection strategy of a-share market based on rotation effect and random forest

Abstract

Due to the random nature of stock market, it is extremely difficult to capture market trends with traditional subjective analysis. Besides, the modeling and forecasting of quantitative investment strategies are not easy. Based on the research of experts and scholars at home and abroad and the rotation effect of large and small styles in China’s A-share market, a stock picking strategy combining wheeling effect and random forest is proposed. Firstly, judge the style trend of the A-share market, that is, the relatively strong style in the large and small-sized market. The strategy first judges the trend of the A-share market style, then uses a multi-factor stock selection model through random forest to select stocks among the constituent stocks of the dominant style index, and buys the selected stocks according to the optimal portfolio weights determined by the principle of minimum variance. The empirical results show that the annualized rate of return of the strategy in the eight years from January 1, 2012 to April 1, 2020 is 3.6% higher than that of the single-round strategy, far exceeding the performance of the CSI 300 Index during the same period.