A review on Ensemble learning based maximal frequent pattern mining over Cloud

In digital era vast quantity of data is produced by smart machines and it is challenging work to store and evaluate the Big data. The frequent pattern mining in Big data plays extremely vital part in industry for decision making process. Ensemble learning is a common machine learning categorization technique that employs multiple learning algorithms to resolve a problem more accurately and predictably in big data. The present system experiences several difficulties, including performance, scalability, parallelism, privacy, and security. This paper examines the overview of several new techniques, algorithms and methodologies in ensemble learning, cloud computing, frequent pattern mining and privacy preservation. This study also makes an attempt to find out appropriate Big data processing framework that are used to generate frequent patterns over cloud using ensemble learning. This paper concludes by giving challenges and future direction in pattern mining using ensemble learning.