Skip to Main Content
Data mining is the process of extracting previously unknown information from an exceedingly large data set with minimum human interference. The useful information may be expressed as relationships between propositions or variables or data elements, which can be used to predict future patterns or behaviour. The present paper investigates evolutionary computing techniques for data mining tasks in the form of discovery of association rules and presents a brief review of evolutionary computation techniques for machine learning systems. The evolution of association rules as subset selection in the best form is comprehensible and modular knowledge for understanding. The experimental results and examples for binary data set are provided to demonstrate the effectiveness of evolutionary computation for rule discovery tasks in form of association rules.