August 08, 2012
Over recent years, global markets have increasingly relied on high performance computing resources to process financial transactions at blistering speeds. While the practice is meant to increase trading volume and market liquidity, high frequency trading (HFT) has displayed some disturbing side effects. In 2010, HFTs were largely blamed for a 1,014-point swing on the Dow Jones Industrial Average, known as the “Flash Crash.” More recently, an algorithmic bug was found responsible for nearly bankrupting Knight Capital Partners. Today, Time Business posted an article taking a closer look at HFT technologies and the risks they pose to financial markets.
High frequency trading is the method financial institutions use to process massive amounts of trades in short amounts of time. It’s not uncommon for a high frequency trader application to execute thousands or millions of trades in one second. The technology, which is based on high speed HPC-like clusters, super-fast network connections and sophisticated analytics software, has been around for nearly a decade and has experienced a rapid increase of adoption on Wall Street over the past five years.
The algorithms behind these systems can make decisions based on small price differences between exchanges. For example, if Apple’s stock was selling for $621.95 in the US and $620.00 overseas, an HFT system would buy the cheaper stock and sell the more expansive one. This would result in a near-immediate and risk free profit for the firm.
On a small scale, the model appear to make perfect sense: it makes money for the trader and increases market liquidity for everyone. But some estimate that nearly 70 percent of all market activity originates from high frequency trades. This means that people actually analyzing the worth of a company with the purpose of long-term investing are in the minority.
Given the ratio of traditional versus high frequency traders, it appears that a majority of market transactions are simply reactions to a small group of deliberately made trades. Add any number of programming bugs to this phenomenon and HFT systems have the ability to bring a market to its knees. In last week’s case involving Knight Capital Partners, a bug in a trading algorithm was ultimately blamed for the firm’s loss of $440 million.
Financial professionals and regulators seem very aware of the risks HFT systems pose, but the technology’s popularity is outpacing regulators’ ability to control it. Last December, Dave Cliff, a computer science professor at the University of Bristol and HFT veteran, spoke of these risks in an interview with HFT Review, remarking “One of the things that we have focused on . . . for the last five years is the extent on which the global financial markets are now essentially a single, planetary-wide, ultra-large scale complex IT system . . . The 6th May Flash Crash was the first real sign that actually our concern was justified, that events could happen at an unprecedented scale, in terms of the magnitude of the drop and the speed at which it happened.”
Full story at Time Business
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?