An Efficient Market Basket Analysis based on Adaptive Association Rule Mining with Faster Rule Generation Algorithm

Abstract

Data mining is the process of extracting relatively useful information from a large data base. Majority of the recognized business organizations, super markets, etc., have accumulated huge amount of information from their customers. A vital sub problem of data mining is to identify frequent sets to assist mine association rules for Market Basket Analysis (MBA). Market Basket Analysis is an effective data mining tool utilized to discover the co-occurrence or co-existence of nominal or categorical observations. MBA is extensively used to identify purchasing pattern of customers in a supermarkets using transaction level data. However, it is very tough to find the valuable information hidden in large databases. Many researches were done by the database community based on association rule mining and classification technique to find the related information in large databases. The most widely used technique to conduct Market Basket Analysis is association rules technique. In this paper, an effective MBA based on Adaptive Association Rule Mining with Faster Rule Generation Algorithm (FRG-AARM) is proposed based on Adaptive Association Rule Mining. This algorithm speeds up the rule mining process with better accuracy and effectiveness