A Multiple Classifier Approach to Improving Classification Accuracy Using Big Data Analytics Tool

Abstract

At the heart of analytics is data. Data analytics has become an indispensable part of intelligent decision making in the current digital scenario. Applications today generate a large amount of data. Associated with the data deluge, data analytics field has seen an onset of a large number of open source tools and software to expedite large scale analytics. Data science community is robust with numerous options of tools available for storing, processing and analysing data. This research paper makes use of KNIME, one of the popular tools for big data analytics, to perform an investigative study of the key classification algorithms in machine learning. The comparative study shows that the classification accuracy can be enhanced by using a combination of the learning techniques and proposes an ensemble technique on publicly available datasets.