As evolutionary computing (EC) becomes a mature area of computer science, researchers and practitioners in other domains including engineering, medicine and finance are adopting evolutionary and related natural computing methodologies in order to solve problems in their own applications area. Although there has always been interaction between the domains of EC and finance/economics, it is noticeable that there has been an increasing volume of research at this interface in recent years. EvoFIN 2010 is the fourth edition of this event, specifically dedicated to the applications of EC (and related natural computing methodologies) to finance and economics.

Interesting synergies exist between the methodological issues faced by researchers in computational finance and economics, and those faced by researchers in other Evo* application domains. Applications such as optimisation, model induction, clustering and classification span multiple domains and therefore novel EC methodologies, or novel applications of these, are of common interest to attendees at multiple events. Financial environments are typically hard, being dynamic, noisy and co-evolutionary. These environments serve as an excellent test bed for novel evolutionary methodologies. It is anticipated that this event will assist in a useful two-way flow of ideas between the finance/economics community and the EC community.

EvoFIN 2010 focuses primarily on the use of EC and related natural computing techniques in computational finance and economics. High quality paper submissions which demonstrate novelty in terms of methodology, application or both, are strongly encouraged. Applications of interest include (but are not limited to):

• algorithmic trading
• forecasting financial time series
• portfolio selection and management
• pricing complex financial products
• developing risk management systems
• financial engineering

Other applications of interest include artificial stock markets and agent-based models of related social processes. Methodologies of interest include EC methodologies such as genetic programming, genetic algorithms and evolutionary strategies, as well as other natural computing methodologies such as particle swarm, foraging algorithms, artificial immune systems, hybrid systems, and multi-agent systems.

Accepted papers will appear in the proceedings of Evo*, published in a volume of the Springer Lecture Notes in Computer Science, which will be available at the Conference.

Accepted papers can be found here.

Submit your manuscript, at most 10 A4 pages long, in Springer LNCS format no later than November 4, 2009 using the online submission tool at http://myreview.csregistry.org/evoapplications10/.
Please refer to Springer LNCS web site for the paper formatting instructions.

Submissions must be original and not published elsewhere, and will be peer reviewed by at least two members of the program committee.
The review process is double-blind and therefore the paper must not contain any references that would identify the authors.

The authors of accepted papers will have to improve their paper on the basis of the reviewers' comments and will be asked to send a camera ready version of their manuscripts.

At least one author of each accepted paper has to register for the conference no later than the early registration deadline, and at least one author has to attend the conference and present the paper.