Thumbnail - Request a copy

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

Desmet, Pierre (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 Aurifeille, Jacques-Marie; Deissenberg, Christophe, Bio-Mimetic Approaches in Management Science, Springer : Berlin Heidelberg, p. 61-75

Type
Chapitre d'ouvrage
Date
1998
Book title
Bio-Mimetic Approaches in Management Science
Book author
Aurifeille, Jacques-Marie; Deissenberg, Christophe
Publisher
Springer
Published in
Berlin Heidelberg
ISBN
978-0792349938
Pages
61-75
Metadata
Show full item record
Author(s)
Desmet, Pierre
Dauphine Recherches en Management [DRM]
Abstract (EN)
In comparison with other usual statistical methods (MCO, logistic regression, discriminant analysis, AID), advantages of neural network with backpropagation are numerous and well known (non linear effects, distribution flee 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.
Subjects / Keywords
empirical results; direct marketing; scoring; algorithm; bio mimetic; neural networks
JEL
G24 - Investment Banking; Venture Capital; Brokerage; Ratings and Ratings Agencies
M31 - Marketing
C45 - Neural Networks and Related Topics