"Quantifying Return Distributions in Financial Markets Using High Frequency Data"
Supervised by: Dr. Tobias Preis, Warwick Business School, and Prof. Eugene Stanley, Center for Polymer Studies and Department of Physics, Boston University.
The big data challenge has recently drawn the attention of many different fields of science, ranging from physics, statistics, pure and applied mathematics, and in general in the field of complex systems science. In this work we investigate the behaviour and the decision making process of people acting in financial markets. A huge amount of data is available from electronic recording of financial transactions. Here we analyse a secondly dataset of the stocks forming the Dow Jones Industrial Average in the period from 2008 to mid 2010. We quantify the return distributions for high frequency data and find that their tails are consistent with a power law relationship for time scales ranging from 300 seconds to 3600 seconds. For larger time scales, the behaviour changes and we find that some of the distributions become consistent with an exponential decay.