Comparative Analysis of Frequent Pattern Mining for Large Data Using FP-Tree and CP-Tree Methods

Association rule mining plays a crucial role in many of the business organizations like retail, telecommunications, manufacturing, insurance, banking, etc., to identify association among different objects in the dataset. In the process of rule mining, identify frequent patterns, which can help to improve the business decisions. FP-growth and CP-tree are the well-known algorithms to find the frequent patterns. This work performs comparative analysis of FP-growth and CP (compact pattern)-tree based on time and space complexity parameters. The comparative analysis also focuses on scalability parameter with various benchmark dataset sizes. Outcomes of this work help others to choose the algorithm to implement in their application.