Non-Hierarchichal Network Evolutionary System

March 13, 2009

The Evolutionary Computation Congress Cycle

Filed under: Congress — jjmerelo @ 4:37 pm

There are three main EC conferences in the yearly calendar: GECCO, Genetic and Evolutionary Computation Conference, which takes place usually around July in far away places like Canada and London and is organized by the ACM, CEC, Congress on Evolutionary Computation, which also travels around the world but never gets close to Spain, takes place by the end of May/beginning of June, and then Evostar, which is mainly an European event, held in cozy places to an enthusiastic audience.
I’ve never been in CEC, just once in GECCO , and several times in Evostar. From a strictly personal point of view, Evostar is probably the best, but scientifically GECCO is tops, with 5-6 reviewers per paper, a very strong scientif committee, and usually quite interesting keynotes. Papers accepted in GECCO’s main tracks do undergo a reviewing process stronger than many conferences.
All this introduction is meant to say that our project will be this year in all the conferences in the cycle. We’ll be presenting a paper on CEQA at Evostar, our multikulti algorithm at CEC, and another paper on multikulti and a joint work with Christian Gagné at GECCO, as we recently knew yesterday.
So, if you’re attending any of these EC conferences this year, there will be somebody from this project. See you there!

March 12, 2009

New chapter on prediction of book loses in companies

In such crisis times as these, the recently released chapter “Finding relevant variables in a financial distress prediction problem using Genetic Programming and Self-Organizing Maps” from volume 2 of “Natural Computing in Computational Finance” can come in quite handy.

In it we use Genetic Programming to generate models of prediction of book loses in companies, and we tackle the problem of finding the relevant variables for the prediction using Genetic Programming and Kohonen’s Self Organising Maps. This approach singificantly reduces the number of variables used for the analysis, while minimising the prediction error.

In other words, we tell you what you have to look at if you want to avoid losing money in your company – but don’t hold us responsible if you don’t like the results!

The chapter can also be obtained from SpringerLink.

You should also check our financial prediction tool PRESAGI

Create a free website or blog at