Exploration of Relationship between Symmetric Confirmation Measures and Association Thresholds

• 발행기관: 한국자료분석학회
• 저자명: Hee Chang Park
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.15 No.4, 1723~1731쪽, 전체 9쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2013.08.30

영문 초록

Data mining is the process of sorting through a massive volume database and discovering useful information. One of the well-studied problems in data mining is association rule technique. An association rule technique finds the relation among itemsets in a big database. Some interestingness measures have been developed in association rule mining. Such interestingness measures are divided into objective, subjective, and semantic measures. In this paper we investigated the relationship between symmetric confirmation measures and association thresholds, and checked the conditions of interestingness measures by Piatetsky-Shapiro. And then we inquired into the some properties for these measure. The comparative studies with support, confidence, and lift were shown by numerical examples. As a result, we found that symmetric confirmation measures is better than support, confidence, and lift because these measures have the direction of the association.

목차

1. Introduction

2. Symmetric confirmation measures and association thresholds

3. Numerical example

4. Conclusion

References

키워드

Association rule confidence lift support symmetric confirmation measure