Machine learning for direct marketing response models : Bayesian networks with evolutionary programming

Research output: Journal PublicationsJournal Article (refereed)

75 Citations (Scopus)

Abstract

Machine learning methods are powerful tools for data mining with large noisy databases and give researchers the opportunity to gain new insights into consumer behavior and to improve the performance of marketing operations. To model consumer responses to direct marketing, this study proposes Bayesian networks learned by evolutionary programming. Using a large direct marketing data set, we tested the endogeneity bias in the recency, frequency, monetary value (RFM) variables using the control function approach; compared the results of Bayesian networks with those of neural networks, classification and regression tree (CART), and latent class regression; and applied a tenfold cross-validation. The results suggest that Bayesian networks have distinct advantages over the other methods in accuracy of prediction, transparency of procedures, interpretability of results, and explanatory insight. Our findings lend strong support to Bayesian networks as a robust tool for modeling consumer response and other marketing problems and for assisting management decision making.
Original languageEnglish
Pages (from-to)597-612
Number of pages16
JournalManagement Science
Volume52
Issue number4
DOIs
Publication statusPublished - 1 Apr 2006

Fingerprint

Bayesian networks
Evolutionary programming
Machine learning
Direct marketing
Marketing
Consumer response
Transparency
Data mining
Modeling
Recency
Neural networks
Learning methods
Latent class
Control function
Cross-validation
Classification and regression trees
Consumer behaviour
Management decision-making
Data base
Prediction

Keywords

  • Bayesian networks
  • Data mining
  • Direct marketing
  • Evolutionary programming
  • Machine learning

Cite this

@article{6f2ac29ae1ce4612b93db97723d0ba69,
title = "Machine learning for direct marketing response models : Bayesian networks with evolutionary programming",
abstract = "Machine learning methods are powerful tools for data mining with large noisy databases and give researchers the opportunity to gain new insights into consumer behavior and to improve the performance of marketing operations. To model consumer responses to direct marketing, this study proposes Bayesian networks learned by evolutionary programming. Using a large direct marketing data set, we tested the endogeneity bias in the recency, frequency, monetary value (RFM) variables using the control function approach; compared the results of Bayesian networks with those of neural networks, classification and regression tree (CART), and latent class regression; and applied a tenfold cross-validation. The results suggest that Bayesian networks have distinct advantages over the other methods in accuracy of prediction, transparency of procedures, interpretability of results, and explanatory insight. Our findings lend strong support to Bayesian networks as a robust tool for modeling consumer response and other marketing problems and for assisting management decision making.",
keywords = "Bayesian networks, Data mining, Direct marketing, Evolutionary programming, Machine learning",
author = "Geng CUI and WONG, {Man Leung} and LUI, {Hon Kwong}",
year = "2006",
month = "4",
day = "1",
doi = "10.1287/mnsc.1060.0514",
language = "English",
volume = "52",
pages = "597--612",
journal = "Management Science",
issn = "0025-1909",
publisher = "INFORMS Institute for Operations Research and the Management Sciences",
number = "4",

}

Machine learning for direct marketing response models : Bayesian networks with evolutionary programming. / CUI, Geng; WONG, Man Leung; LUI, Hon Kwong.

In: Management Science, Vol. 52, No. 4, 01.04.2006, p. 597-612.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Machine learning for direct marketing response models : Bayesian networks with evolutionary programming

AU - CUI, Geng

AU - WONG, Man Leung

AU - LUI, Hon Kwong

PY - 2006/4/1

Y1 - 2006/4/1

N2 - Machine learning methods are powerful tools for data mining with large noisy databases and give researchers the opportunity to gain new insights into consumer behavior and to improve the performance of marketing operations. To model consumer responses to direct marketing, this study proposes Bayesian networks learned by evolutionary programming. Using a large direct marketing data set, we tested the endogeneity bias in the recency, frequency, monetary value (RFM) variables using the control function approach; compared the results of Bayesian networks with those of neural networks, classification and regression tree (CART), and latent class regression; and applied a tenfold cross-validation. The results suggest that Bayesian networks have distinct advantages over the other methods in accuracy of prediction, transparency of procedures, interpretability of results, and explanatory insight. Our findings lend strong support to Bayesian networks as a robust tool for modeling consumer response and other marketing problems and for assisting management decision making.

AB - Machine learning methods are powerful tools for data mining with large noisy databases and give researchers the opportunity to gain new insights into consumer behavior and to improve the performance of marketing operations. To model consumer responses to direct marketing, this study proposes Bayesian networks learned by evolutionary programming. Using a large direct marketing data set, we tested the endogeneity bias in the recency, frequency, monetary value (RFM) variables using the control function approach; compared the results of Bayesian networks with those of neural networks, classification and regression tree (CART), and latent class regression; and applied a tenfold cross-validation. The results suggest that Bayesian networks have distinct advantages over the other methods in accuracy of prediction, transparency of procedures, interpretability of results, and explanatory insight. Our findings lend strong support to Bayesian networks as a robust tool for modeling consumer response and other marketing problems and for assisting management decision making.

KW - Bayesian networks

KW - Data mining

KW - Direct marketing

KW - Evolutionary programming

KW - Machine learning

UR - http://commons.ln.edu.hk/sw_master/2163

U2 - 10.1287/mnsc.1060.0514

DO - 10.1287/mnsc.1060.0514

M3 - Journal Article (refereed)

VL - 52

SP - 597

EP - 612

JO - Management Science

JF - Management Science

SN - 0025-1909

IS - 4

ER -