Cyclic Association Rules Mining under Constraints

TL;DR

This paper introduces CBCAR, a new constraint-based method for mining cyclic association rules that effectively reduces irrelevant rules and improves performance in discovering cyclic item correlations.

Contribution

The paper presents CBCAR, a novel algorithm that efficiently mines cyclic association rules under constraints, addressing limitations of previous methods.

Findings

CBCAR reduces the number of irrelevant rules.

The approach improves mining performance.

Experiments demonstrate its usefulness.

Abstract

Several researchers have explored the temporal aspect of association rules mining. In this paper, we focus on the cyclic association rules, in order to discover correlations among items characterized by regular cyclic variation overtime. The overview of the state of the art has revealed the drawbacks of proposed algorithm literatures, namely the excessive number of generated rules which are not meeting the expert's expectations. To overcome these restrictions, we have introduced our approach dedicated to generate the cyclic association rules under constraints through a new method called Constraint-Based Cyclic Association Rules CBCAR. The carried out experiments underline the usefulness and the performance of our new approach.