Data mining of association structures to model consumer behaviour

被引：39

作者：

Giudici, P ^{[1
]}

Passerone, G ^{[1
]}

机构：

[1] Univ Pavia, Dipartimento Econ Polit & Metodi Quantitat, I-27100 Pavia, Italy

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 2002年 / 38卷 / 04期

关键词：

Bayesian model selection; graphical log linear models; market basket analysis; Markov chain Monte Carlo methods; odds ratios;

D O I：

10.1016/S0167-9473(01)00077-9

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We describe how statistical association models and, specifically, log linear and graphical models, can be usefully employed to study consumer behaviours. We describe some methodological problems related to the implementation of discrete graphical models for market basket analysis data. In particular, we shall discuss model selection procedures, (C) 2002 Elsevier Science B.V. All rights reserved.

引用

页码：533 / 541

页数：9

共 8 条

[1]

Brooks SP, 1998, J ROY STAT SOC D-STA, V47, P69, DOI 10.1111/1467-9884.00117

[2] Decomposable graphical Gaussian model determination [J].

Giudici, P ;

Green, PJ .

BIOMETRIKA, 1999, 86 (04) :785-801

[3]

GIUDICI P, 2001, IN PRESS MACH LEARNI

[4]

HECKERMAN D, 1995, MACH LEARN, V20, P197, DOI 10.1007/BF00994016

[5]

Lauritzen S.L., 1996, Graphical models, V17, P298

[6] BAYESIAN GRAPHICAL MODELS FOR DISCRETE-DATA [J].

MADIGAN, D ;

YORK, J .

INTERNATIONAL STATISTICAL REVIEW, 1995, 63 (02) :215-232

[7]

PASSERONE G, 2000, ATT CONV SUGI IT

[8]

Whittaker J, 1990, GRAPHICAL MODELS APP

← 1 →