Electronic trading in global markets andexchanges requires sophisticated communication and datamanagement systems. Novel computational infrastructures andtrading strategies are required to support the massive amountof incoming streaming data, where the main problem is inlatency management. Multi-agent Systems have been recognizedas a promising solution to address complex problems in manyareas such as biology, social sciences and financial markets andmay provide powerful and flexible solutions for implementingtrading engines. In addition, reconfigurable hardware based onField Programmable Gate Arrays (FPGAs) offers manyimportant performance benefits over software implementations,such as reducing decision making latency and high-throughputdata processing. Robust and scalable trading engines can bedeveloped by leveraging the benefits of reconfigurable FPGAplatforms. This paper presents a multi-agent architecture inreconfigurable hardware for financial applications and theimplementation of a trading engine for pre-trade analysis as avalidation scenario. Performance results show that calculationof technical indicators and trading strategy evaluation togenerate trading signals with a latency of 550 ns is achievable.
|Title of host publication||Unknown Host Publication|
|Number of pages||8|
|Publication status||Published (in print/issue) - 27 Mar 2014|
|Event||IEEE Computational Intelligence for Financial Engineering and Economics - Canary Wharf, London|
Duration: 27 Mar 2014 → …
|Conference||IEEE Computational Intelligence for Financial Engineering and Economics|
|Period||27/03/14 → …|