Stock portfolio selection balancing variance and tail risk via stock vector representation acquired from price data and texts
Stock portfolio selection balancing variance and tail risk via stock vector representation acquired from price data and texts
复制标题
DOI：
10.1016/j.knosys.2022.108917
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Xin Du;Kumiko Tanaka-Ishii
中科院分区：
文献类型：
--
作者：
Xin Du;Kumiko Tanaka-Ishii
最近关于投资组合选择的研究报告了除了价格变动之外还结合文本数据的方法。价格、文本和事件作为底层的内容采用异构数据形式，因此在没有任何一致的数学公式的情况下进行处理。在本文中，我们建议通过在嵌入向量空间（我们称之为具有事件分布（NESTED）的NEws-STock空间）中表示所有相关对象（股票、新闻、事件）来概括投资组合选择。 NESTED 形成内积向量空间（希尔伯特空间），其中文本和股票表示为通过事件分布获取的向量（嵌入）。在本文中，我们首先在 NESTED 上从理论上重新表述马科维茨的投资组合优化问题。我们展示了我们的新公式如何有可能更好地纳入尾部风险，尾部风险在文本数据中得到了更好的体现。获取此类嵌入的一种典型方法是通过神经计算。我们通过在三个市场的 24 个新闻价格数据集上使用它获得的实验结果表明，所生成的投资组合的负尾部的帕累托指数在所有市场中都增加了，这证明股票嵌入捕获了尾部风险。我们的方法显示尾部风险和非尾部风险之间的平衡得到了很大的改善，增益提高了 45.5%，信息比率提高了 59.4%。
Recent works on portfolio selection report ways to incorporate textual data in addition to price movements. Price, texts, and events as what lies underneath take heterogeneous data form and therefore have been processed without any consistent mathematical formulation.In this article, we propose to generalize portfolio selection by representing all related objects (stocks, news, events) in an embedding vector space, that we call aNEws-STock space with Event Distribution(NESTED). A NESTED forms an inner product vector space (Hilbert space), in which texts and stocks are represented as vectors (embeddings), acquired through a distribution of events. In this article, we first theoretically reformulate Markowitz’s portfolio optimization problem on NESTED. We show how our new formulation has the potential to better incorporate the tail risk, which is represented better in textual data.One typical method to acquire such embeddings is via neural computing. Our experimental results, obtained by using it on 24 news-price datasets across three markets, showed that the Pareto’s exponent in the negative tail of the generated portfolios increased in all markets, which is evidence that the stock embeddings captured the tail risks. Our method showed a large improvement balancing between the tail risk and non-tail risk, up to 45.5% larger gain and 59.4% larger Information ratio.