Evolutionary and Immune Algorithms Applied to Association Rule Mining in Static and Stream Data

Abstract

Data generation has grown rapidly over the recent years. Different types of products and services are offered daily on the Internet. Finding out elegant, flexible and robust strategies to deal with this amount of data in a static way is one goal of data mining, whilst the data stream mining works in dynamic environments. The searching of co-occurrence of items in data is a task of a data miming branch named association rule mining. The present paper investigates the use of evolutionary algorithms as well as artificial immune systems to extract association rules within item sets in both, static and dynamic, environments. We perform a number of experiments over datasets from the association rule mining literature, and compare their performances. A discussion in terms of computational time and measures of interest is made to conclude the proposed study.