FUZZY ARTMAP for continuous data

I was going through an IEEE research paper which has used Fuzzy ARTMAP for predicting the price of electricity given some highly correlated data.

As per my basic understanding about Fuzzy ARTMAP, it is a classification algorithm, so how will it be able to predict continuous data?

The text from research paper is:

In the architecture of the FA network, the preprocessing stages take the input vector and contribute to produce complement coding, which avoids category proliferation, i.e., the creation of a relatively large number of categories to represent the training data. A sequence of input vectors (price and demand) and their respective target vectors are introduced to the FA network in order to classify the input pattern correctly. The classified input patterns are then grouped into labels using membership functions.

I was using MATLAB to implement the same. So is there a library in MATLAB to approach towards the solution?