Neural Networks in Finance

4 Evaluation of Network Estimation

So far we have discussed the structure or architecture of a network, as well as the ways of training or estimating the coefficients or weights of a network. How do we interpret the results obtained from these networks, relative to what we can obtain from a linear approximation?

There are three sets of criteria: in-sample criteria, out-of-sample criteria, and common sense based on tests of significance and the plausibility of the results.

4.1 In-Sample Criteria

When evaluating the regression, we first want to know how well a model fits the actual data used to obtain the estimates of the coefficients. In the neural network literature, this is known as supervised training. We supervise the network, insofar as ...