Mining Frequent ItemSet Based on Clustering of Bit Vectors

Objectives: In data mining, finding frequent item set from voluminous databases is an important role. It is a challenging task to find item sets frequently arise in the exponential growth of the databases. The number of scans to find the frequent item set is assessed as more and created redundancy. Methods/Statistical analysis: In this research work, a new technique is applied to improve the reduction in number of scans and minimize the redundancy. An algorithm is developed to mine the frequent item set using clustering techniques. A cluster table of frequent item set is created with minimal number of scanning. Findings: The support count is fixed to eliminate the duplicates which minimize the redundancy. This algorithm is appreciable, because the intermediate data in the dataset can be reused. The efficiency of algorithm can be identified by seeing the experimental results that is significantly performed well than the exiting algorithms. Applications/Improvements: In future, other algorithms are applied for the same data set to test its effectiveness in order to minimize the redundancy which avoids wastage of the memory space.