Techniques of acceleration for association rule induction with pseudo artificial life algorithm

Masaaki Kanakubo, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

Frequent patterns mining is one of the important problems in data mining. Generally, the number of potential rules grows rapidly as the size of database increases. It is therefore hard for a user to extract the association rules. To avoid such a difficulty, we propose a new method for association rule induction with pseudo artificial life approach. The proposed method is to decide whether there exists an item set which contains N or more items in two transactions. If it exists, a series of item sets which are contained in the part of transactions will be recorded. The iteration of this step contributes to the extraction of association rules. It is not necessary to calculate the huge number of candidate rules. In the evaluation test, we compared the extracted association rules using our method with the rules using other algorithms like Apriori algorithm. As a result of the evaluation using huge retail market basket data, our method is approximately 10 and 20 times faster than the Apriori algorithm and many its variants.

Original languageEnglish
JournalIEEJ Transactions on Electronics, Information and Systems
Volume128
Issue number6
DOIs
Publication statusPublished - 2008

Fingerprint

Association rules
Data mining

Keywords

  • Artificial life
  • Association rules
  • Data mining

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{ebd4e06f89ac4afebbc882a6049b2498,
title = "Techniques of acceleration for association rule induction with pseudo artificial life algorithm",
abstract = "Frequent patterns mining is one of the important problems in data mining. Generally, the number of potential rules grows rapidly as the size of database increases. It is therefore hard for a user to extract the association rules. To avoid such a difficulty, we propose a new method for association rule induction with pseudo artificial life approach. The proposed method is to decide whether there exists an item set which contains N or more items in two transactions. If it exists, a series of item sets which are contained in the part of transactions will be recorded. The iteration of this step contributes to the extraction of association rules. It is not necessary to calculate the huge number of candidate rules. In the evaluation test, we compared the extracted association rules using our method with the rules using other algorithms like Apriori algorithm. As a result of the evaluation using huge retail market basket data, our method is approximately 10 and 20 times faster than the Apriori algorithm and many its variants.",
keywords = "Artificial life, Association rules, Data mining",
author = "Masaaki Kanakubo and Masafumi Hagiwara",
year = "2008",
doi = "10.1541/ieejeiss.128.997",
language = "English",
volume = "128",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "6",

}

TY - JOUR

T1 - Techniques of acceleration for association rule induction with pseudo artificial life algorithm

AU - Kanakubo, Masaaki

AU - Hagiwara, Masafumi

PY - 2008

Y1 - 2008

N2 - Frequent patterns mining is one of the important problems in data mining. Generally, the number of potential rules grows rapidly as the size of database increases. It is therefore hard for a user to extract the association rules. To avoid such a difficulty, we propose a new method for association rule induction with pseudo artificial life approach. The proposed method is to decide whether there exists an item set which contains N or more items in two transactions. If it exists, a series of item sets which are contained in the part of transactions will be recorded. The iteration of this step contributes to the extraction of association rules. It is not necessary to calculate the huge number of candidate rules. In the evaluation test, we compared the extracted association rules using our method with the rules using other algorithms like Apriori algorithm. As a result of the evaluation using huge retail market basket data, our method is approximately 10 and 20 times faster than the Apriori algorithm and many its variants.

AB - Frequent patterns mining is one of the important problems in data mining. Generally, the number of potential rules grows rapidly as the size of database increases. It is therefore hard for a user to extract the association rules. To avoid such a difficulty, we propose a new method for association rule induction with pseudo artificial life approach. The proposed method is to decide whether there exists an item set which contains N or more items in two transactions. If it exists, a series of item sets which are contained in the part of transactions will be recorded. The iteration of this step contributes to the extraction of association rules. It is not necessary to calculate the huge number of candidate rules. In the evaluation test, we compared the extracted association rules using our method with the rules using other algorithms like Apriori algorithm. As a result of the evaluation using huge retail market basket data, our method is approximately 10 and 20 times faster than the Apriori algorithm and many its variants.

KW - Artificial life

KW - Association rules

KW - Data mining

UR - http://www.scopus.com/inward/record.url?scp=72349099646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72349099646&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.128.997

DO - 10.1541/ieejeiss.128.997

M3 - Article

AN - SCOPUS:72349099646

VL - 128

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 6

ER -