Market-basket analysis with principal component analysis: An exploration

Kitty S Y Chiu; Wing Pong Robert Luk; Chun Chung Chan; Fu Lai Korris Chung

Market-basket analysis with principal component analysis: An exploration

Kitty S Y Chiu, Wing Pong Robert Luk, Chun Chung Chan, Fu Lai Korris Chung

Research output: Journal article publication › Conference article › Academic research › peer-review

Abstract

Market-basket analysis is a well-known business problem, which can be (partially) solved computationally using association rules, mined from transaction data to maximize cross-selling effects. Here, we model the market-basket analysis as a finite mixture density of human consumption behavior according to social and cultural events. This leads to the use of principle component analysis and possibly mixture density analysis of transaction data, which was not apparent before. We compare PCA and association rules mined from a set of benchmark transaction data, to explore similarities and differences between these two data exploration tools.

Original language	English
Pages (from-to)	300-305
Number of pages	6
Journal	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume	3
Publication status	Published - 1 Dec 2002
Event	2002 IEEE International Conference on Systems, Man and Cybernetics - Yasmine Hammamet, Tunisia Duration: 6 Oct 2002 → 9 Oct 2002

Keywords

Association rules
Market-basket
Mixture density
PCA

ASJC Scopus subject areas

Control and Systems Engineering
Hardware and Architecture

Cite this

@article{97dc44ab298442eea3000001a3074b1b,

title = "Market-basket analysis with principal component analysis: An exploration",

abstract = "Market-basket analysis is a well-known business problem, which can be (partially) solved computationally using association rules, mined from transaction data to maximize cross-selling effects. Here, we model the market-basket analysis as a finite mixture density of human consumption behavior according to social and cultural events. This leads to the use of principle component analysis and possibly mixture density analysis of transaction data, which was not apparent before. We compare PCA and association rules mined from a set of benchmark transaction data, to explore similarities and differences between these two data exploration tools.",

keywords = "Association rules, Market-basket, Mixture density, PCA",

author = "Chiu, {Kitty S Y} and Luk, {Wing Pong Robert} and Chan, {Chun Chung} and Chung, {Fu Lai Korris}",

year = "2002",

month = dec,

day = "1",

language = "English",

volume = "3",

pages = "300--305",

journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

issn = "0884-3627",

publisher = "IEEE",

note = "2002 IEEE International Conference on Systems, Man and Cybernetics ; Conference date: 06-10-2002 Through 09-10-2002",

}

TY - JOUR

T1 - Market-basket analysis with principal component analysis: An exploration

AU - Chiu, Kitty S Y

AU - Luk, Wing Pong Robert

AU - Chan, Chun Chung

AU - Chung, Fu Lai Korris

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Market-basket analysis is a well-known business problem, which can be (partially) solved computationally using association rules, mined from transaction data to maximize cross-selling effects. Here, we model the market-basket analysis as a finite mixture density of human consumption behavior according to social and cultural events. This leads to the use of principle component analysis and possibly mixture density analysis of transaction data, which was not apparent before. We compare PCA and association rules mined from a set of benchmark transaction data, to explore similarities and differences between these two data exploration tools.

AB - Market-basket analysis is a well-known business problem, which can be (partially) solved computationally using association rules, mined from transaction data to maximize cross-selling effects. Here, we model the market-basket analysis as a finite mixture density of human consumption behavior according to social and cultural events. This leads to the use of principle component analysis and possibly mixture density analysis of transaction data, which was not apparent before. We compare PCA and association rules mined from a set of benchmark transaction data, to explore similarities and differences between these two data exploration tools.

KW - Association rules

KW - Market-basket

KW - Mixture density

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=0038684481&partnerID=8YFLogxK

M3 - Conference article

SN - 0884-3627

VL - 3

SP - 300

EP - 305

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

T2 - 2002 IEEE International Conference on Systems, Man and Cybernetics

Y2 - 6 October 2002 through 9 October 2002

ER -

Market-basket analysis with principal component analysis: An exploration

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this