Pattern mining algorithms for data streams using itemset

Abstract

Knowledge discovery and data mining are fast growing fields of study that span a variety of disciplines, including distributed systems, databases, artificial intelligence, visualization, statistics, high-performance computing, and parallel computing. Raw data is collected by people in business, science, medicine, academia, and government, and there are various commercial programmes that process the data to provide general and specific purpose knowledge discovery. “Turn Data into Knowledge” is an important goal in knowledge discovery and data mining. Data mining is the process of examining data previously stored in databases in order to solve problems. The technique of detecting patterns in vast data repositories is known as data mining. In order to complete a data mining task, effective exploratory strategies are always required. Association rules, correlations, sequential patterns, classification, clustering, and other data mining techniques are only a few examples. Every technique has its own value, which is determined by the application area and challenges for which it is used. The objectives of this study, as stated in the synopsis, are met using association rule mining methodology. The original motivation for association rules mining was the problem of supermarket transaction data. The problem with supermarket transaction data is that it is used to investigate client purchasing habits. The frequency with which things have been purchased together is described by association rules. For instance, the association rule “cool drink=> chips (80%)" implies that 80% of customers who purchase cool drink also purchase chips. Such criteria can be beneficial in making judgments about store layout, product pricing, and marketing, among other things.