Title :
A comprehensive survey of association rules on quantitative data in data mining
Author :
Gosain, Anjana ; Bhugra, Maneela
Author_Institution :
Univ. Sch. of Inf. & Commun. Technol., GGSIP Univ., New Delhi, India
Abstract :
The discovery of association rules is one of the very important tasks in data mining. Association rules help in the generation of more general and qualitative knowledge which in turn helps in decision making. Association rules deal with transactions of both binary values and quantitative data.[9] The traditional algorithms for mining association rules are built on binary attributes databases, which has two limitations. Firstly, it can not concern quantitative attributes; secondly, it treats each item with the same significance although different item may have different significance[6]. Also binary association rules suffers from sharp boundary problems[18]. Moreover many real world transactions consist of quantitative attributes. That is why several researchers have been working on generation of association rules for quantitative data. This paper presents different algorithms given by various researches to generate association rules among quantitative data. We have done comparative analysis of different algorithms for association rules based on various parameters.
Keywords :
data mining; association rule discovery; binary association rule; binary attributes database; binary value; data mining; decision making; qualitative knowledge; quantitative attribute; quantitative data; real world transaction; sharp boundary problem; Algorithm design and analysis; Association rules; Communications technology; Correlation; Itemsets; apriori algorithm; association rules; confidence; data mining; fuzzy set; support;
Conference_Titel :
Information & Communication Technologies (ICT), 2013 IEEE Conference on
Conference_Location :
JeJu Island
Print_ISBN :
978-1-4673-5759-3
DOI :
10.1109/CICT.2013.6558244