Set-Oriented Mining for Association Rules in Relational Databases

M.A.W. Houtsma; Arun Swami

doi:10.1109/ICDE.1995.380413

Set-Oriented Mining for Association Rules in Relational Databases

M.A.W. Houtsma, Arun Swami

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

156 Citations (Scopus)

249 Downloads (Pure)

Abstract

Describe set-oriented algorithms for mining association rules. Such algorithms imply performing multiple joins and may appear to be inherently less efficient than special-purpose algorithms. We develop new algorithms that can be expressed as SQL queries, and discuss the optimization of these algorithms. After analytical evaluation, an algorithm named SETM emerges as the algorithm of choice. SETM uses only simple database primitives, viz. sorting and merge-scan join. SETM is simple, fast and stable over the range of parameter values. The major contribution of this paper is that it shows that at least some aspects of data mining can be carried out by using general query languages such as SQL, rather than by developing specialized black-box algorithms. The set-oriented nature of SETM facilitates the development of extensions

Original language	English
Title of host publication	Proceedings of the Eleventh International Conference on Data Engineering, ICDE 1995
Place of Publication	Los Alamitos, CA
Publisher	IEEE
Pages	25-33
ISBN (Print)	0-8186-69101
DOIs	https://doi.org/10.1109/ICDE.1995.380413
Publication status	Published - 21 Feb 1995
Event	11th International Conference on Data Engineering, ICDE 1995 - Taipei Duration: 6 Mar 1995 → 10 Mar 1995 Conference number: 11

Other

Other	11th International Conference on Data Engineering, ICDE 1995
Abbreviated title	ICDE
City	Taipei
Period	6/03/95 → 10/03/95

Access to Document

10.1109/ICDE.1995.380413

ArticleFinal published version, 713 KB

156 Citations
1 Report

Set-Oriented Mining for Association Rules
Houtsma, M. A. W. & Swami, A., 1993, Stanford: IBM Research Division. 19 p. (IBM Research Report; no. RJ 9567)
Research output: Book/Report › Report › Professional

Cite this

@inproceedings{56af84ed47e7499289a489e6aa8a14b6,

title = "Set-Oriented Mining for Association Rules in Relational Databases",

abstract = "Describe set-oriented algorithms for mining association rules. Such algorithms imply performing multiple joins and may appear to be inherently less efficient than special-purpose algorithms. We develop new algorithms that can be expressed as SQL queries, and discuss the optimization of these algorithms. After analytical evaluation, an algorithm named SETM emerges as the algorithm of choice. SETM uses only simple database primitives, viz. sorting and merge-scan join. SETM is simple, fast and stable over the range of parameter values. The major contribution of this paper is that it shows that at least some aspects of data mining can be carried out by using general query languages such as SQL, rather than by developing specialized black-box algorithms. The set-oriented nature of SETM facilitates the development of extensions",

author = "M.A.W. Houtsma and Arun Swami",

year = "1995",

month = feb,

day = "21",

doi = "10.1109/ICDE.1995.380413",

language = "English",

isbn = "0-8186-69101",

pages = "25--33",

booktitle = "Proceedings of the Eleventh International Conference on Data Engineering, ICDE 1995",

publisher = "IEEE",

address = "United States",

note = "11th International Conference on Data Engineering, ICDE 1995, ICDE ; Conference date: 06-03-1995 Through 10-03-1995",

}

TY - GEN

T1 - Set-Oriented Mining for Association Rules in Relational Databases

AU - Houtsma, M.A.W.

AU - Swami, Arun

N1 - Conference code: 11

PY - 1995/2/21

Y1 - 1995/2/21

N2 - Describe set-oriented algorithms for mining association rules. Such algorithms imply performing multiple joins and may appear to be inherently less efficient than special-purpose algorithms. We develop new algorithms that can be expressed as SQL queries, and discuss the optimization of these algorithms. After analytical evaluation, an algorithm named SETM emerges as the algorithm of choice. SETM uses only simple database primitives, viz. sorting and merge-scan join. SETM is simple, fast and stable over the range of parameter values. The major contribution of this paper is that it shows that at least some aspects of data mining can be carried out by using general query languages such as SQL, rather than by developing specialized black-box algorithms. The set-oriented nature of SETM facilitates the development of extensions

AB - Describe set-oriented algorithms for mining association rules. Such algorithms imply performing multiple joins and may appear to be inherently less efficient than special-purpose algorithms. We develop new algorithms that can be expressed as SQL queries, and discuss the optimization of these algorithms. After analytical evaluation, an algorithm named SETM emerges as the algorithm of choice. SETM uses only simple database primitives, viz. sorting and merge-scan join. SETM is simple, fast and stable over the range of parameter values. The major contribution of this paper is that it shows that at least some aspects of data mining can be carried out by using general query languages such as SQL, rather than by developing specialized black-box algorithms. The set-oriented nature of SETM facilitates the development of extensions

U2 - 10.1109/ICDE.1995.380413

DO - 10.1109/ICDE.1995.380413

M3 - Conference contribution

SN - 0-8186-69101

SP - 25

EP - 33

BT - Proceedings of the Eleventh International Conference on Data Engineering, ICDE 1995

PB - IEEE

CY - Los Alamitos, CA

T2 - 11th International Conference on Data Engineering, ICDE 1995

Y2 - 6 March 1995 through 10 March 1995

ER -

Set-Oriented Mining for Association Rules in Relational Databases

Abstract

Other

Access to Document

Fingerprint

Research output

Set-Oriented Mining for Association Rules

Cite this