Equity Clusters through the Lens of Realized Semicorrelations

We rely on newly-developed realized semicorrelations constructed from high-frequency returns<br>together with hierarchical clustering and cross-validation techniques to identify groups<br>of individual stocks that share common features. Implementing the new procedures based<br>on intraday data for the S&P 100 constituents spanning 2019-2020, we uncover distinct<br>changes in the "optimal" groupings of the stocks coincident with the onset of the COVID-<br>19 pandemic. Many of the clusters estimated with data post-January 2020 evidence clear<br>differences from conventional industry type classifications. They also differ from the clusters<br>estimated with standard realized correlations, underscoring the advantages of "looking<br>inside" the correlation matrix through the lens of the new realized semicorrelations.

我们依靠由高频收益构建的新开发的已实现半相关性，连同层次聚类和交叉验证技术，来识别具有共同特征的个股群组。基于2019 - 2020年标准普尔100指数成分股的日内数据实施新程序，我们发现与新冠疫情爆发同时发生的股票“最优”分组的明显变化。用2020年1月之后的数据估计的许多聚类明显不同于传统的行业类型分类。它们也不同于用标准已实现相关性估计的聚类，这凸显了通过新的已实现半相关性视角“深入观察”相关性矩阵的优势。