z-logo
open-access-imgOpen Access
Present State-of-The-ART of Dynamic Association Rule Mining Algorithms
Author(s) -
N. Satyavathi,
Dr.B. Rama,
Dr.A. Nagaraju
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a4107.119119
Subject(s) - association rule learning , apriori algorithm , data mining , computer science , a priori and a posteriori , k optimal pattern discovery , affinity analysis , association (psychology) , machine learning , philosophy , epistemology
Association Rule Mining (ARM) is a data mining approach for discovering rules that reveal latent associations among persisted entity sets. ARM has many significant applications in the real world such as finding interesting incidents, analyzing stock market data and discovering hidden relationships in healthcare data to mention few. Many algorithms that are efficient to mine association rules are found in the existing literature, apriori-based and Pattern-Growth. Comprehensive understanding of them helps data mining community and its stakeholders to make expert decisions. Dynamic update of association rules that have been discovered already is very challenging due to the fact that the changes are arbitrary and heterogeneous in the kind of operations. When new instances are added to existing dataset that has been subjected to ARM, only those instances are to be used in order to go for incremental mining of rules instead of considering the whole dataset again. Recently some algorithms were developed by researchers especially to achieve incremental ARM. They are broadly grouped into Apriori-based and Pattern-Growth. This paper provides review of Apriori-based and Pattern-Growth techniques that support incremental ARM.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here