%0 Journal Article
%T Backward Support Computation Method for Positive and Negative Frequent Itemset Mining
%A Mrinmoy Biswas Akash
%A Indrani Mandal
%A Md. Selim Al Mamun
%J Journal of Data Analysis and Information Processing
%P 37-48
%@ 2327-7203
%D 2023
%I Scientific Research Publishing
%R 10.4236/jdaip.2023.111003
%X Association rules mining is a major data mining field that leads to
discovery <span>of associations and correlations
among items in today¡¯s big data enviro</span>nment. The conventional
association rule mining focuses mainly on positive itemsets generated from
frequently occurring itemsets (PFIS). However, there has been a significant
study focused on infrequent itemsets with utilization of negative association
rules to mine interesting frequent itemsets (NFIS) from transactions. In this
work, we propose an efficient backward calculating negative frequent itemset
algorithm namely <i>EBC-NFIS</i> for computing backward su<span>pports that can extract both positive and negative
frequent itemse</span>ts syn<span>chronously from
dataset. EBC-NFIS algorithm is based on popular <i>e-NF</i></span><i>IS</i> algorithm that computes supports of negative itemsets from the supports of
positive itemsets. The proposed algorithm makes use of previously computed
supports from memory to minimize the computation time. In addition, association
rules, <i>i.e.</i> positive and negative
association rules (PNARs) are generated from discovered frequent itemsets using
EBC-NFIS algorithm. The efficiency of the proposed algorithm is verified by
several experiments and comparing results with e-NFIS algorithm. The
experimental results confirm that <span>the
proposed algorithm successfully discovers NFIS and PNARs and runs</span> significantly faster than conventional e-NFIS algorithm.
%K Data Mining
%K Positive Frequent Itemset
%K Negative Frequent Itemset
%K Association Rule
%K Backward Support
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=122850