nokia_investors — Nokia investor trading correlations (1998-2002)

Description

Temporal correlation networks among the investors that traded the Nokia stock on the Helsinki stock exchange between January 1998 and December 2002, from Ranganathan et al. The data come from the central register of shareholdings of the Finnish central securities depository (Euroclear Finland), which records the daily trades of all Finnish households and institutions (foreign investors are excluded). For each investor, the daily net volume (the number of shares bought minus the number of shares sold, averaged over a week) was computed, and the Pearson correlation of the net volumes of each pair of investors was measured over six-month windows of 126 trading days, shifted by one month (21 trading days), giving 54 windows. In each window, only the investors that traded on at least 20 days are included, and all pairs of them are connected, i.e. the network of each window is a complete graph. The analysis was done separately for three categories of investors, which correspond to the three networks below; there are no edges between investors of different categories. The edges of all windows are combined into a single multigraph, with the window given as an edge property. Investor identifiers are anonymized.

households: Finnish household investors (54 windows).
non_financial: non-financial institutions (54 windows).
financial: financial institutions (only 27 of the 54 windows are included in the distributed data).

The networks have the following properties:

Nodes: investor_id, the anonymized identifier of the investor.
Edges: weight, the Pearson correlation coefficient between the daily net volumes of the two investors in the window; time, the date that labels the window in the source data (as a Unix timestamp), which appears to be the first trading day of the window, since it ranges from January 1998 to June 2002.

Tags

Economic Weighted Temporal Multigraph Metadata

Citation

S. Ranganathan, M. Kivelä, J. Kanniainen, "Dynamics of investor spanning trees around dot-com bubble." PLOS ONE 13(6), e0198807 (2018) 10.1371/journal.pone.0198807 Sci-Hub
S. Ranganathan, M. Kivelä, J. Kanniainen, "Data from: Dynamics of investor spanning trees around dot-com bubble." Dryad, dataset (2018) 10.5061/dryad.5b8n621 Sci-Hub

Upstream URL OK

https://doi.org/10.5061/dryad.5b8n621

Upstream license

Creative Commons CC0 1.0 Universal, https://creativecommons.org/publicdomain/zero/1.0/

Networks

Tip: click on a column header to sort the list, or hover over it for a description.

Column legend

$\left<k\right>$: Mean degree
$\sigma_k$: Standard deviation of the degrees
$\lambda_h$: Largest eigenvalue of the Hashimoto (non-backtracking) matrix
$\tau$: Random walk mixing time
$r$: Degree assortativity
$c$: Global clustering coefficient
$\oslash$: (Pseudo-) diameter
$S$: Relative size of the largest component
NPs: Node properties
EPs: Edge properties

Name	Nodes	Edges	$\left<k\right>$	$\sigma_k$	$\lambda_h$	$\tau$	$r$	$c$	$\oslash$	$S$	Kind	Mode	NPs	EPs	gt	GraphML	GML	csv
households	2,821	6,653,266	4716.96	4159.15	1500.78	1.91	0.04	0.84	2	1.00	Undirected	Unipartite	investor_id	weight time	20.1 MiB	56.6 MiB	53.9 MiB	40.6 MiB
non_financial	627	432,308	1378.97	1313.06	339.00	1.88	0.01	0.84	2	1.00	Undirected	Unipartite	investor_id	weight time	1.5 MiB	3.6 MiB	3.4 MiB	2.6 MiB
financial	76	15,899	418.39	295.20	59.37	0.78	-0.01	0.94	2	1.00	Undirected	Unipartite	investor_id	weight time	86 KiB	136 KiB	127 KiB	97 KiB