Association Rule Mining Based on Hybrid Whale Optimization Algorithm

Na Deng, Zhiwei Ye, Wenhui Cai, Mingwei Wang, Aixin Zhang, Wen Zhou, Zimei Wei, Daxin Zhu

OAI: oai:igi-global.com:308817 • DOI: 10.4018/IJDWM.308817

Association Rule Mining(ARM) is one of the most significant and active research areas in data mining. Recently, Whale Optimization Algorithm (WOA) has been successfully applied in the field of data mining, however, it easily falls into the local optimum. Therefore, an improved WOA based adaptive parameter strategy and Levy Flight mechanism (LWOA) is applied to mine association rules. Meanwhile, a hybrid strategy that blends two algorithms to balance the exploration and exploitation phases is put forward, that is, grey wolf optimization algorithm (GWO), artificial bee colony algorithm (ABC) and cuckoo search algorithm (CS) are devoted to improving the convergence of LWOA. The approach performs a global search and finds the association rules sets by modeling the rule mining task as a multi-objective problem that simultaneously meets support, confidence, lift, and certain factor, which is examined on multiple data sets. Experimental results verify that the proposed method has better mining performance compared to other algorithms involved in the paper.

Data Mining Computer Science and Information Technology Data Mining and Databases