Neural networks are effective in detecting fraud because they can:
A.
discover new trends since they are inherently linear.
B.
solve problems where large and general sets of training data are not obtainable.
C.
attack problems that require consideration of a large number of input variables.
D.
make assumptions about the shape of any curve relating variables to the output.
Explanation:
Neural networks can be used to attack problems that require consideration of numerous input variables. They are capable of capturing relationships and patterns often missed by other statistical methods, but they will not discover new trends. Neural networks are inherently nonlinear and make no assumption about the shape of any curve relating variables to the output. Neural networks will not work well at solving problems for which sufficiently large and general sets of training data are not obtainable.