摘要
通过研究邻近森林算法在股票交易中的应用,将邻近森林分类模型与自动化交易订单相结合得到交易信号分类模型。首先,将分类模型与指数均线策略相结合得到交易信号的双层过滤模型。其次,通过均幅指标和凯利公式确定自动化订单的定价策略、选股和确定份额的交易策略;最后,将双层过滤模型与定价策略、交易策略相结合得到基于邻近森林算法的量化交易系统。仿真实验显示,该系统平均年回报率达到20.09%,相较于只依靠指数均线的策略,邻近森林算法在盈利上的优势更明显。
By studying the application of the neighboring forest algorithm in stock trading,a trading signal classification model is obtained by combining the neighboring forest classification model with automated trading orders.Firstly,the classification model is combined with the index moving average strategy to obtain a dual layer filtering model for trading signals.Then,the pricing strategy for automated orders,stock selection,and trading strategy for determining shares are determined through the average amplitude indicator and Kelly formula;Finally,the double-layer filtering model is combined with pricing and trading strategies to obtain a quantitative trading system based on the proximity forest algorithm.Simulation experiments show that the average annual return rate of the system reaches 20.09%.Compared to the strategy relying solely on the exponential moving average,the neighboring forest algorithm has a more significant advantage in profitability.
作者
吴灿柳
陈小英
WU Canliu;CHEN Xiaoying(School of Computer Science and Technology,Wuhan University of Technology,Wuhan 430070,China;Hubei Credit Information Center,Wuhan 430071,China)
出处
《软件导刊》
2024年第10期82-87,共6页
Software Guide
