IBM Develops 'World's Fastest Financial Analysis' System
Scientists at IBM Research collaborated with TD Securities during the project, which IBM said achieved a 21-times performance improvement on the volume of data consumed by today's financial trading systems.
Financial service companies such as stock brokerages rely on analysis of fixed snapshots of financial data streaming through their trading systems to make buy and sell decisions. But the volume of options and equities trading traffic has doubled every year since 2003, spurred, in part, by increased electronic trading. IBM said some systems today process up to 2 million transaction messages per second.
That means traditional approaches to capturing and analyzing trading data is increasingly inadequate. Scientists in IBM's research division created a prototype "stream processing system" that analyzes live, streaming data from a nearly unlimited number of sources. The new system is based on IBM's Blue Gene/P supercomputer and the InfoSphere Streams software developed by IBM Research.
IBM said the system provided "astoundingly low latency," the amount of time between when data is received and when it's acted upon, and was capable of handling data at 21 times the speed of the Options Price Reporting Authority (OPRA), the world's largest market data feed.
"In the constantly evolving electronic marketplace, innovative technology solutions to better manage high volumes of realtime information are a significant competitive edge," Rizwan Khalfan, CIO of TD Securities, said in a statement.
The collaboration with TD Securities is part of IBM's First-Of-A-Kind program that pairs IBM research scientists with customers to develop leading-edge technologies.