Implementing neural networks for decision support in direct marketing

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

16 Citations (Scopus)

Abstract

Innovative methods of artificial intelligence such as artificial neural networks (ANNs) have been increasingly adopted to predict consumer responses to direct marketing. However, appropriate learning algorithms, evaluation criteria, and validation procedures are necessary for effective implementation of neural networks to provide decision support to managers. This study compares the performance of Bayesian neural networks with that of logistic regression and the backpropagation method in modelling consumer responses. The results of a tenfold stratified cross-validation suggest that although the three methods perform equally well under the error rate, Bayesian neural networks generate higher statistics for the Area under the Receiver Operating Characteristic Curve (AUROC) and cumulative lifts. The findings suggest that researchers should adopt effective learning algorithms, relevant evaluation criteria and appropriate validation procedures for neural networks to model consumer responses and solve marketing problems facing today's businesses.
Original languageEnglish
Pages (from-to)235-254, 263
JournalInternational Journal of Market Research
Volume46
Issue number2
Publication statusPublished - 1 Jan 2004

Fingerprint

Neural networks
Decision support
Direct marketing
Consumer response
Learning algorithm
Evaluation criteria
Receiver operating characteristic curve
Back propagation
Artificial intelligence
Marketing
Modeling
Logistic regression
Artificial neural network
Managers
Statistics
Cross-validation

Cite this

@article{e204cc2d91d044738a85b028c371d441,
title = "Implementing neural networks for decision support in direct marketing",
abstract = "Innovative methods of artificial intelligence such as artificial neural networks (ANNs) have been increasingly adopted to predict consumer responses to direct marketing. However, appropriate learning algorithms, evaluation criteria, and validation procedures are necessary for effective implementation of neural networks to provide decision support to managers. This study compares the performance of Bayesian neural networks with that of logistic regression and the backpropagation method in modelling consumer responses. The results of a tenfold stratified cross-validation suggest that although the three methods perform equally well under the error rate, Bayesian neural networks generate higher statistics for the Area under the Receiver Operating Characteristic Curve (AUROC) and cumulative lifts. The findings suggest that researchers should adopt effective learning algorithms, relevant evaluation criteria and appropriate validation procedures for neural networks to model consumer responses and solve marketing problems facing today's businesses.",
author = "Geng CUI and MAN, {Leung Wong}",
year = "2004",
month = "1",
day = "1",
language = "English",
volume = "46",
pages = "235--254, 263",
journal = "International Journal of Market Research",
issn = "1470-7853",
publisher = "Market Research Society",
number = "2",

}

Implementing neural networks for decision support in direct marketing. / CUI, Geng; MAN, Leung Wong.

In: International Journal of Market Research, Vol. 46, No. 2, 01.01.2004, p. 235-254, 263.

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

TY - JOUR

T1 - Implementing neural networks for decision support in direct marketing

AU - CUI, Geng

AU - MAN, Leung Wong

PY - 2004/1/1

Y1 - 2004/1/1

N2 - Innovative methods of artificial intelligence such as artificial neural networks (ANNs) have been increasingly adopted to predict consumer responses to direct marketing. However, appropriate learning algorithms, evaluation criteria, and validation procedures are necessary for effective implementation of neural networks to provide decision support to managers. This study compares the performance of Bayesian neural networks with that of logistic regression and the backpropagation method in modelling consumer responses. The results of a tenfold stratified cross-validation suggest that although the three methods perform equally well under the error rate, Bayesian neural networks generate higher statistics for the Area under the Receiver Operating Characteristic Curve (AUROC) and cumulative lifts. The findings suggest that researchers should adopt effective learning algorithms, relevant evaluation criteria and appropriate validation procedures for neural networks to model consumer responses and solve marketing problems facing today's businesses.

AB - Innovative methods of artificial intelligence such as artificial neural networks (ANNs) have been increasingly adopted to predict consumer responses to direct marketing. However, appropriate learning algorithms, evaluation criteria, and validation procedures are necessary for effective implementation of neural networks to provide decision support to managers. This study compares the performance of Bayesian neural networks with that of logistic regression and the backpropagation method in modelling consumer responses. The results of a tenfold stratified cross-validation suggest that although the three methods perform equally well under the error rate, Bayesian neural networks generate higher statistics for the Area under the Receiver Operating Characteristic Curve (AUROC) and cumulative lifts. The findings suggest that researchers should adopt effective learning algorithms, relevant evaluation criteria and appropriate validation procedures for neural networks to model consumer responses and solve marketing problems facing today's businesses.

UR - http://commons.ln.edu.hk/sw_master/2577

M3 - Journal Article (refereed)

VL - 46

SP - 235-254, 263

JO - International Journal of Market Research

JF - International Journal of Market Research

SN - 1470-7853

IS - 2

ER -