RP4: Complex Network Analysis in Stock Markets (WP2)



The research project aims to study investor behaviour and the dynamics of corporate ownership, especially during financial crises via complex network analysis and big data techniques. The researcher will study in depth large financial data sets, including a unique dataset of complete trading records from all Finnish investors on publicly traded domestic stocks along with background information on traders’ transactions and their attributes (e.g., individual/institutional, male/female, location, and size of the position with unique trader IDs) from 1995 to 2009 (covering the Millennium IT bubble and recent financial crises).

The first part of this RP will provide solid empirical results on investor networks by linking traders with similar portfolio rebalancing and trading strategies. We aim to
(i) study how empirical investor networks change during crises and to
(ii) identify the determinants of different rebalancing and trading strategies (e.g., is it announcements or volatility that drives a certain group of investors to trade).
The second part will analyse the determinants and dynamics of corporate ownership during financial crises.

We expect to provide empirical evidence on the determinants of ownership base and dynamics, behavioural differences between different investor groups (e.g., major institutional investors and individual small-scale investors), how ownership structure reflects the industrial sector of the stocks (e.g., energy sector vs IT during the Millennium IT bubble), and how different investors react to news announcement and process the public information. This data-intensive analysis is very essential to gaining an understanding of the empirical properties of the financial markets and the behaviour of investors. Financial supervisory bodies can benefit from the study to understand the impacts of macro variables on stock markets and to advise monetary policy makers. Private sectors can use the results to obtain insight into and advice on corporate strategies. Companies can use these results to understand how ownership base affects the dynamics of the underlying stock and investors to predict the nature of information diffusion in financial markets.

Early Stage Resercher working on the project: Kestutis Baltakys

Supervisor: Professor Juho Kanniainen, Tampere University of Technology / juho.kanniainen(at)tut.fi

TUT logo