Neural networks for estimation and prediction
Clearly, since neural networks produce continuous output, they may quite naturally be used for estimation and prediction. Suppose, for example, that we are interested in predicting the price of a particular stock three months in the future. Presumably, we would have encoded price information using the min-max normalization above. However, the neural network would output a value between 0 and 1, Which (one would hope) does not represent the predicted price of the stock.