Big data frequent itemset mining

Abstract

Big data takes its fame from analyzing the data gathered from various sources. This process is called Big data analytics that includes multiple techniques, each one differs from the others by the data used, and the results earned. But they share the same purpose, which is the improvement of decision-making. In this manuscript, we aim to present one of the famous analytic techniques, frequent itemset mining. That seeks to find the frequent patterns in a transactional database and decipher the association rules among those patterns, therefore, using this knowledge to make decisions based on those patterns. Our purpose is to introduce the big data process to mine the frequent itemset using Spark’s machine-learning library, and Python.