In comparison with other usual statistical methods (MCO, logistic regression, discriminant analysis, AID), advantages of neural network with retropropagation are numerous and well known (non linear effects, distribution free variables, low sensibility to outliers or missing variables). However, implementation and efficiency have not yet received a strong interest. The paper reviews comparative analyses and presents results obtained for prediction of a behaviour in fund-raising.
DESMET, P. (1998). Comparison of the Predictability of a Neural Network with Retropropagation with Those using Linear Regression, Logistic and A.I.D. Methods for Direct Marketing Scoring. In: Bio-Mimetic Approaches in Management Science. 1st ed. Kluwer Academic Publishers, pp. 61-75.