dorsal/arxiv
View SchemaCorrelation matrix decomposition of WIG20 intraday fluctuations
| Authors | R. Rak, S. Drozdz, J. Kwapien, P. Oswiecimka |
|---|---|
| Categories | |
| ArXiv ID | physics/0606041 |
| URL | https://arxiv.org/abs/physics/0606041 |
| Journal | Acta Physica Polonica B 37, 3123-3132 (2006) |
Abstract
Using the correlation matrix formalism we study the temporal aspects of the Warsaw Stock Market evolution as represented by the WIG20 index. The high frequency (1 min) WIG20 recordings over the time period between January 2001 and October 2005 are used. The entries of the correlation matrix considered here connect different distinct periods of the stock market dynamics, like days or weeks. Such a methodology allows to decompose the price fluctuations into the orthogonal eigensignals that quantify different modes of the underlying dynamics. The magnitudes of the corresponding eigenvalues reflect the strengths of such modes. One observation made in this paper is that strength of the daily trend in the WIG20 dynamics systematically decreases when going from 2001 to 2005. Another is that large events in the return fluctuations are primarily associated with a few most collective eigensignals.
{
"annotation_id": "8a03a316-fad6-4eca-b086-b9fb07eb6582",
"date_created": "2026-03-02T18:01:10.128000Z",
"date_modified": "2026-03-02T18:01:10.128000Z",
"file_hash": "572c1f61aba01daf6ea3057f272c453c7b64e3d20ee57288e91a6c4ec1dc75a6",
"private": false,
"record": {
"abstract": "Using the correlation matrix formalism we study the temporal aspects of the\nWarsaw Stock Market evolution as represented by the WIG20 index. The high\nfrequency (1 min) WIG20 recordings over the time period between January 2001\nand October 2005 are used. The entries of the correlation matrix considered\nhere connect different distinct periods of the stock market dynamics, like days\nor weeks. Such a methodology allows to decompose the price fluctuations into\nthe orthogonal eigensignals that quantify different modes of the underlying\ndynamics. The magnitudes of the corresponding eigenvalues reflect the strengths\nof such modes. One observation made in this paper is that strength of the daily\ntrend in the WIG20 dynamics systematically decreases when going from 2001 to\n2005. Another is that large events in the return fluctuations are primarily\nassociated with a few most collective eigensignals.",
"arxiv_id": "physics/0606041",
"authors": [
"R. Rak",
"S. Drozdz",
"J. Kwapien",
"P. Oswiecimka"
],
"categories": [
"physics.data-an",
"cond-mat.stat-mech",
"physics.soc-ph",
"q-fin.ST"
],
"journal_ref": "Acta Physica Polonica B 37, 3123-3132 (2006)",
"title": "Correlation matrix decomposition of WIG20 intraday fluctuations",
"url": "https://arxiv.org/abs/physics/0606041"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "530f1543-6249-4111-b6a0-851a5ba1cec5",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}