Besides the original individual set generated by the GA, we define a subset of it with a small number of antecedents as a filtered set.  A novel method of extracting important system components, known as <it> open product analysis <\it>, is applied to these two sets, yielding systems that perform well with a small number of antecedents.  The fuzzy classifier we reduced performs well using only 10% to 30% of the antecedents that were originally used for classification.