Clustbigfim: Mapreduce Cf For Big Data Itemset Mining

• Author(s):

  KOUSALYADEVI S | ISHWARYA L

• Keywords:

  Frequent Itemset Mining, MapReduce, K-means Clustering, BigFIM, Apriori, Eclat, Big Data, Scalable Pattern Discovery.

• Abstract:

  Frequent Itemset Mining (FIM) Is Essential For Discovering Patterns In Large-scale Data, But Traditional Algorithms Struggle With Big Data Volumes Due To Scalability Issues. ClustBigFIM Introduces A Hybrid MapReduce-based Framework That Integrates Parallel K-means Clustering As Preprocessing To Partition Datasets Into Manageable Clusters, Followed By Modified BigFIM Employing Apriori And Eclat Algorithms For Efficient Extraction Of Frequent Itemsets. In The MapReduce Paradigm, The Map Phase Computes Distances And Assigns Itemsets To Clusters, While The Reduce Phase Aggregates Results And Generates Patterns Useful For Business Analytics Like Market Basket Analysis. Evaluated On Large Synthetic And Real-world Datasets, ClustBigFIM Achieves Superior Speedup, Scalability, And Execution Time Compared To Standalone BigFIM By Reducing Data Redundancy Through Clustering. This Approach Leverages Hadoop’s Fault-tolerant Processing To Handle Petabyte-scale Data, Enabling Robust FIM In Distributed Environments.

---

Other Details

• Paper id:

  IJSARTV12I4105057

• Published in:

  Volume: 12 Issue: 4 April 2026

• Publication Date:

  2026-04-18

Download Article