University of Chinese Academy of Sciences, Beijing, China.
Comput Intell Neurosci. 2022 May 20;2022:4743427. doi: 10.1155/2022/4743427. eCollection 2022.
With the development of artificial intelligence technology, an increasing number of researchers try to apply different machine learning and deep learning methods to quantitative trading fields to obtain more stable and efficient trading models. As a typical quantitative trading strategy, stock selection has also attracted a lot of attention. There are many studies and applications on stock selection. However, the existing research and application cannot meet the continuous expansion of the scale and dimension of stock selection data set and cannot meet the needs in terms of efficiency and accuracy of stock selection. A convolutional neural network has been applied to image classification and achieved better results than the traditional methods. In this study, we first constructed a multifactor stock selection data set based on China's stock market. Then, we apply the convolutional neural network model to analyze stock selection data and select stocks. The main contribution of this study is that we build a stock multifactor data set, construct a "factor picture," and classify them by convolutional neural network to select stocks. This study also makes comparative experiments on the decision tree, support vector machine, and feedforward neural network in stock selection on the same data set constructed in this study. The results show that the stock selection method based on the convolutional neural network outperforms other methods in terms of the annual return, sharp ratio, and max drawdown.
随着人工智能技术的发展，越来越多的研究人员尝试将不同的机器学习和深度学习方法应用于量化交易领域，以获得更稳定、更高效的交易模型。作为一种典型的量化交易策略，股票选择也吸引了大量的关注。已经有许多关于股票选择的研究和应用。然而，现有的研究和应用无法满足股票选择数据集规模和维度的不断扩大，也无法满足在股票选择的效率和准确性方面的需求。卷积神经网络已被应用于图像分类，并取得了比传统方法更好的结果。在本研究中，我们首先构建了一个基于中国股票市场的多因素股票选择数据集。然后，我们应用卷积神经网络模型来分析股票选择数据并选择股票。本研究的主要贡献在于，我们构建了一个股票多因素数据集，构建了“因子图片”，并通过卷积神经网络对其进行分类以选择股票。本研究还在基于本研究构建的相同数据集上对决策树、支持向量机和前馈神经网络在股票选择方面进行了对比实验。结果表明，基于卷积神经网络的股票选择方法在年回报率、夏普比率和最大回撤方面优于其他方法。
