dorsal/arxiv
View SchemaSpectral and network methods in the analysis of correlation matrices of stock returns
| Authors | Tapio Heimo, Jari Saramaki, Jukka-Pekka Onnela, Kimmo Kaski |
|---|---|
| Categories | |
| ArXiv ID | physics/0703061 |
| URL | https://arxiv.org/abs/physics/0703061 |
| DOI | 10.1016/j.physa.2007.04.124 |
| Journal | Physica A 383, 147-151 (2007) |
Abstract
Correlation matrices inferred from stock return time series contain information on the behaviour of the market, especially on clusters of highly correlating stocks. Here we study a subset of New York Stock Exchange (NYSE) traded stocks and compare three different methods of analysis: i) spectral analysis, i.e. investigation of the eigenvalue-eigenvector pairs of the correlation matrix, ii) asset trees, obtained by constructing the maximal spanning tree of the correlation matrix, and iii) asset graphs, which are networks in which the strongest correlations are depicted as edges. We illustrate and discuss the localisation of the most significant modes of fluctuation, i.e. eigenvectors corresponding to the largest eigenvalues, on the asset trees and graphs.
{
"annotation_id": "73a412d2-0d2f-4d91-86c1-c88351c9386b",
"date_created": "2026-03-02T18:01:17.361000Z",
"date_modified": "2026-03-02T18:01:17.361000Z",
"file_hash": "52e17b74858aaaa6b8c095d6a7341f2435ef0d23ce3e13532779fc51da0b2d39",
"private": false,
"record": {
"abstract": "Correlation matrices inferred from stock return time series contain\ninformation on the behaviour of the market, especially on clusters of highly\ncorrelating stocks. Here we study a subset of New York Stock Exchange (NYSE)\ntraded stocks and compare three different methods of analysis: i) spectral\nanalysis, i.e. investigation of the eigenvalue-eigenvector pairs of the\ncorrelation matrix, ii) asset trees, obtained by constructing the maximal\nspanning tree of the correlation matrix, and iii) asset graphs, which are\nnetworks in which the strongest correlations are depicted as edges. We\nillustrate and discuss the localisation of the most significant modes of\nfluctuation, i.e. eigenvectors corresponding to the largest eigenvalues, on the\nasset trees and graphs.",
"arxiv_id": "physics/0703061",
"authors": [
"Tapio Heimo",
"Jari Saramaki",
"Jukka-Pekka Onnela",
"Kimmo Kaski"
],
"categories": [
"physics.soc-ph"
],
"doi": "10.1016/j.physa.2007.04.124",
"journal_ref": "Physica A 383, 147-151 (2007)",
"title": "Spectral and network methods in the analysis of correlation matrices of stock returns",
"url": "https://arxiv.org/abs/physics/0703061"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "15f09276-6123-49dd-ac8d-a139bf34491f",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}