Wirth, Philipp; Medda, Francesca; Schröder, Thomas; (2025) A Modularity-Spectral Algorithm for Equity Market Structure Segmentation. The Journal of Financial Data Science , 7 (4) pp. 46-64. 10.3905/jfds.2025.1.201.

Text JFDS-2025.pdf - Accepted Version Access restricted to UCL open access staff Download (1MB)

Abstract

Understanding hidden market structures is crucial for identifying diversifiers to manage portfolio risk. Detecting such market structures, however, is nontrivial. To solve this problem, we introduce the Dynamic modularity-spectral algorithm (DynMSA), a novel approach to identify clusters of stocks with high intra-cluster correlations and low inter-cluster correlations, thereby achieving a more effective risk-reducing portfolio allocation. We applied DynMSA to constituents of the S&P 500 and compared the results to sector- and market-based benchmarks. Besides the conception of this algorithm, our contributions further include implementing a sector-based calibration for modularity optimization and a correlation-based distance function for spectral clustering. Testing revealed that DynMSA outperforms baseline models in intra- and inter-cluster correlation differences. Importantly, DynMSA identified stocks misclassified by traditional sector methodologies and offered optimized portfolios with higher absolute and risk-adjusted returns. Additionally, our algorithm enables practitioners to build automated portfolios based on the S&P 500.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item