R-Diffset vs. IR-Diffset: Comparison Analysis in Dense and Sparse Data

Abstract

The mining of concealed information from databases using Association Rule Mining seems to be promising. The successful extraction of this information will give a hand to many areas by aiding them in the process of finding solutions, economic projecting, commercialization policies, medical inspections, and numbers of other problems. ARM is the most outstanding method in the mining of remarkable related configurations from any groups of information. The important patterns encountered are categorized as recurrent/frequent and non-recurrent/infrequent. Most of the previous data mining methods concentrated on horizontal data set-ups. Nevertheless, recent studies have shown that vertical data formats are becoming the main concerns. One example of vertical data format is Rare Equivalence Class Transformation (R-Eclat). Due to its efficacy, R-Eclat algorithms have been commonly applied for the processing of large datasets. The R-Eclat algorithm is actually comprised of four types of variants. However, our work will only focus on the R-Diffset variant and Incremental R-Diffset (IR-Diffset). The performance analysis of the R-Diffset and IR-Diffset algorithms in the mining of sparse and dense data are compared. The processing time for R-Diffset algorithm, especially for sequential processing is very long. Thus, the incremental R-Diffset (IR-Diffset) has been established to solve this problem. While R-Diffset may only process the non-recurrent itemsets mining process in sequential form, IR-Diffset on the other hand has the capability to execute sequential data that have been fractionated. The advantages of this newly developed IR-Diffset may become a potential candidate in providing a time-efficient data mining process, especially those involving the large sets of data.