Hierarchical PCA and Modeling Asset Correlations

2020/10/08 by Marco Avellaneda, Avellaneda, Marco, Juan Andrés Serur +1
Decision Sciences · Economics, Econometrics and Finance · #Complex Systems and Time Series Analysis #FOS: Economics and business #Financial Risk and Volatility Modeling #Mathematical Finance (q-fin.MF) #Stock Market Forecasting Methods #q-fin.MF

paper · pdf · doi:10.48550/arxiv.2010.04140

arxiv created 2020/10/08 · openalex publication_date 2020/10/08 · arxiv updated 2020/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Modeling cross-sectional correlations between thousands of stocks, across countries and industries, can be challenging. In this paper, we demonstrate the advantages of using Hierarchical Principal Component Analysis (HPCA) over the classic PCA. We also introduce a statistical clustering algorithm for identifying of homogeneous clusters of stocks, or "synthetic sectors". We apply these methods to study cross-sectional correlations in the US, Europe, China, and Emerging Markets.

Related

• Cluster analysis of stocks using price movements of high frequency data from National Stock Exchange
• Identifying Highly Correlated Stocks Using the Last Few Principal Components
• Non-linear correlation analysis in financial markets using hierarchical clustering
• Hierarchical PCA and Applications to Portfolio Management
• Homogeneity and Sub-homogeneity Pursuit: Iterative Complement Clustering PCA