Berlin 2012 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

SOE: Fachverband Physik sozio-ökonomischer Systeme

SOE 5: Focus Session: Big Data

SOE 5.2: Hauptvortrag

Montag, 26. März 2012, 15:30–16:00, HE 101

Experimental Computational Finance & Big Data Environment — •Philip Treleaven — University College London, UK

High-frequency algorithmic trading is growing rapidly accounting for 70% of US equity volumes in 2010 (according to Reuters and Bloomberg), but is also of major concern due to potential catastrophic "Flash Crashes". Likewise, the behavior and risk of individual trading algorithms is poorly understood.

For the past seven years UCL has worked with the major investment banks and funds developing algorithmic trading systems, and more recently with the regulators investigating high-frequency trading risk and systemic risk. To support this work we have developed our Algorithmic Trading & Risk Analytics Development Environment (ATRADE) platform which can be used both for virtual and real trading and has access to terabytes of "big" data. It has been designed to: a) speed the development of trading algorithms, b) evaluate algorithm risk, and c) assess algo programmers. As an evaluation of the performance of ATRADE, in 2011 it was used to support a global algorithmic trading competition which attracted over 300 traders in 100 teams scattered across Europe, North America and Australia. Moving forward, UCL is now extending ATRADE with a comprehensive social media engine that supports scraping and analyzing of a wide range of social media data (called Social media Streaming, Repository and Analytics Manager (SocialSTREAM) platform). This presentation will present ATRADE and SocialSTREAM.