Banks trial evolutionary computing approach to ‘breed out’ inefficiency

News

Banks trial evolutionary computing approach to ‘breed out’ inefficiency

Cliff Saran

Four investment banks are piloting a system based on “evolutionary computing” to increase returns on structured derivatives products.

Codefarm, a UK supplier of software tools for the financial markets, has developed a hosted service based on the evolutionary computing method, which aims to deliver greater efficiency through systems that automatically develop the optimum approach to processing tasks.

Inspired by Darwinian principles and modern genetics, evolutionary computing simulates the evolutionary mechanisms – selection of the fittest, genetic re-combination and mutation – to search for optimal solutions that can constantly be improved over time.

Although evolutionary computing has been investigated in academic circles for some time, commercial applications have been limited because the high level of computing power necessary has not been readily available.

Codefarm’s Galapagos online service is using grid computing based on Hewlett-Packard’s Flexible Computing Services to provide the necessary processing power as and when it is required.

The banks are using the Galapagos service to tackle complex numerical modelling problems.


Email Alerts

Register now to receive ComputerWeekly.com IT-related news, guides and more, delivered to your inbox.
By submitting you agree to receive email from TechTarget and its partners. If you reside outside of the United States, you consent to having your personal data transferred to and processed in the United States. Privacy
 

COMMENTS powered by Disqus  //  Commenting policy