A Template Model for Multidimensional Inter-Transactional Association Rules

Ling Feng, Jeffrey Xu Yu, Hongjun Lu, Jiawei Han

Research output: Contribution to journalArticleAcademicpeer-review

30 Citations (Scopus)

Abstract

Multidimensional inter-transactional association rules extend the traditional association rules to describe more general associations among items with multiple properties across transactions. “After McDonald and Burger King open branches, KFC will open a branch two months later and one mile away” is an example of such rules. Since the number of potential inter-transactional association rules tends to be extremely large, mining inter-transactional associations poses more challenges on efficient processing than mining traditional intra-transactional associations. In order to make such association rule mining truly practical and computationally tractable, in this study we present a template model to help users declare the interesting multidimensional inter-transactional associations to be mined. With the guidance of templates, several optimization techniques, i.e., joining, converging, and speeding, are devised to speed up the discovery of inter-transactional association rules. We show, through a series of experiments on both synthetic and real-life data sets, that these optimization techniques can yield significant performance benefits.
Original languageEnglish
Pages (from-to)153-175
Number of pages23
JournalVLDB journal
Volume11
Issue number2
DOIs
Publication statusPublished - 2002

Fingerprint

Association rules
Joining
Processing
Experiments

Keywords

  • DB-DM: DATA MINING
  • Intra-transactional/inter-transactional association rules
  • Multidimensional context
  • Template model

Cite this

Feng, Ling ; Yu, Jeffrey Xu ; Lu, Hongjun ; Han, Jiawei. / A Template Model for Multidimensional Inter-Transactional Association Rules. In: VLDB journal. 2002 ; Vol. 11, No. 2. pp. 153-175.
@article{e3c94729384d4bc4a6d740ddab0ff7a7,
title = "A Template Model for Multidimensional Inter-Transactional Association Rules",
abstract = "Multidimensional inter-transactional association rules extend the traditional association rules to describe more general associations among items with multiple properties across transactions. “After McDonald and Burger King open branches, KFC will open a branch two months later and one mile away” is an example of such rules. Since the number of potential inter-transactional association rules tends to be extremely large, mining inter-transactional associations poses more challenges on efficient processing than mining traditional intra-transactional associations. In order to make such association rule mining truly practical and computationally tractable, in this study we present a template model to help users declare the interesting multidimensional inter-transactional associations to be mined. With the guidance of templates, several optimization techniques, i.e., joining, converging, and speeding, are devised to speed up the discovery of inter-transactional association rules. We show, through a series of experiments on both synthetic and real-life data sets, that these optimization techniques can yield significant performance benefits.",
keywords = "DB-DM: DATA MINING, Intra-transactional/inter-transactional association rules, Multidimensional context, Template model",
author = "Ling Feng and Yu, {Jeffrey Xu} and Hongjun Lu and Jiawei Han",
year = "2002",
doi = "10.1007/s00778-002-0069-6",
language = "English",
volume = "11",
pages = "153--175",
journal = "VLDB journal",
issn = "1066-8888",
publisher = "Springer",
number = "2",

}

A Template Model for Multidimensional Inter-Transactional Association Rules. / Feng, Ling; Yu, Jeffrey Xu; Lu, Hongjun; Han, Jiawei.

In: VLDB journal, Vol. 11, No. 2, 2002, p. 153-175.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A Template Model for Multidimensional Inter-Transactional Association Rules

AU - Feng, Ling

AU - Yu, Jeffrey Xu

AU - Lu, Hongjun

AU - Han, Jiawei

PY - 2002

Y1 - 2002

N2 - Multidimensional inter-transactional association rules extend the traditional association rules to describe more general associations among items with multiple properties across transactions. “After McDonald and Burger King open branches, KFC will open a branch two months later and one mile away” is an example of such rules. Since the number of potential inter-transactional association rules tends to be extremely large, mining inter-transactional associations poses more challenges on efficient processing than mining traditional intra-transactional associations. In order to make such association rule mining truly practical and computationally tractable, in this study we present a template model to help users declare the interesting multidimensional inter-transactional associations to be mined. With the guidance of templates, several optimization techniques, i.e., joining, converging, and speeding, are devised to speed up the discovery of inter-transactional association rules. We show, through a series of experiments on both synthetic and real-life data sets, that these optimization techniques can yield significant performance benefits.

AB - Multidimensional inter-transactional association rules extend the traditional association rules to describe more general associations among items with multiple properties across transactions. “After McDonald and Burger King open branches, KFC will open a branch two months later and one mile away” is an example of such rules. Since the number of potential inter-transactional association rules tends to be extremely large, mining inter-transactional associations poses more challenges on efficient processing than mining traditional intra-transactional associations. In order to make such association rule mining truly practical and computationally tractable, in this study we present a template model to help users declare the interesting multidimensional inter-transactional associations to be mined. With the guidance of templates, several optimization techniques, i.e., joining, converging, and speeding, are devised to speed up the discovery of inter-transactional association rules. We show, through a series of experiments on both synthetic and real-life data sets, that these optimization techniques can yield significant performance benefits.

KW - DB-DM: DATA MINING

KW - Intra-transactional/inter-transactional association rules

KW - Multidimensional context

KW - Template model

U2 - 10.1007/s00778-002-0069-6

DO - 10.1007/s00778-002-0069-6

M3 - Article

VL - 11

SP - 153

EP - 175

JO - VLDB journal

JF - VLDB journal

SN - 1066-8888

IS - 2

ER -