Analisis kinerja algoritma cut both ways dan dynamic itemset counting dalam menghitung maximal frequent itemset pada teknik asisiasi

Abstract

Association Is a technique in data mining used to identify lhe relationship between itemsets in a database (association rule). Some researches In association rule since the Invention d the AIS algorithm In 1993 have yielded several new algorithms. Some of those used artificial datasets (IBM Artificial) and daimed by their authonl to have a reliable performance ln finding maximal frequent ltemset (MFI). But these datasets have different dlaracteriStic from the real wot1d dataset (retail data8ets). The goal d this research Is to evaluate the performance d Dynamic Hemset Counting (DIC) and Cut Both Ways (CBW) ln finding MFI on retail dataset using Apriori as a third party algorittvn. There are 5 datasets used In 1his research which have different number of items and records. We used sman and large values d minimum support (mlnsupp) thresholds as a treatment for each algorithm and dataset, whim are: 0.02%, 0.04%, 0.06%, 0.08%, and 0.10% for