AZTI-Tecnalia has just published a "Recruitment Forecasting Software" which is a fish recruitment prediction software, used to build a robust classifier for fish recruitment prediction with sparse and noisy data. However the software can be used to predict any ecosystem answer where the relation cause effect is unknown but a relation between a number of environmental parameters and the variable to be predicted can be expected.

The methodology consists of 4 steps:

• A semi-automated recruitment discretization method;
• Supervised discretization of predictors;
• Multivariate and non-redundant predictors selection;
• Learning a probabilistic classifier.