Financial services firms must rapidly, capture, process and find value in massive volumes of data in order to maximize client returns and minimize risk. Traditional business intelligence approaches â which rely on capturing, organizing and then querying a fixed snapshot of data â can no longer keep pace.
Through the combination of IBMâs InfoSphere Streams â a breakthrough software technology from IBM Research â and IBMâs Blue Gene/P supercomputer, the IBM Research team created a unique stream processing system ideally suited to meet and surpass the demands of the financial services industry. By enabling rapid, intelligent analysis of live streaming data from a practically unlimited number of sources, IBM delivered astoundingly low latency - the time between when data is received and when itâs acted upon - far surpassing the performance of traditional trading systems.
âIn the constantly evolving electronic marketplace, innovative technology solutions to better manage high volumes of real time information are a significant competitive edge,â said Rizwan Khalfan, Chief Information Officer at TD Securities.
According to the Financial Information Forum, the combined options and equities traffic has exploded, doubling in size every year since 2003. The challenge to ingest, analyze and automatically act upon millions of messages every second is the difference between success and failure for automated trading systems. IBMâs use of its unique stream computing architecture and Blue Gene allowed for significant enhancements to real-time messaging and analytical capabilities while offering a simplified, energy-efficient underlying infrastructure.
The collaboration with TD Securities is part of IBMâs First-Of-A-Kind program (FOAK), which engages IBMâs scientists with the companyâs clients to explore how emerging technologies could solve real world business problems. In this collaboration, IBM Research scientists worked with TD Securities to create a tailored, unique system through applying advanced and emerging technologies and new approaches.
âTD Securities could potentially use the new system to analyze and act on information before their competitors can finish ingesting and analyzing, effectively blinding the competition to its actions,â said Nagui Halim, chief scientist of the Stream Computing Project at IBM. âWeâre not talking about 20 percent faster here. Weâre talking about 20 times faster,â he added.
Todayâs exchange data rates challenge financial firms trading systems to process up to two million messages per second. The goal of any automated trading systems is to reduce the time between the receipt of market data messages and the decision, achieving a very low latency while processing extreme amounts of data. The more messages a system can process, the more decisions can be made; hence, the more valuable the system.
In testing, the system was found to be capable of handling data at 21 times the speed of Options Price Reporting Authority (OPRA), the worldâs single largest market data feed, while maintaining ultra low end-to-end latencies.