A Comparison of Various Classification Techniques in Big Data Mining

Big Data is a term that refers to an extremely large volume of datasets such that traditional database and software techniques are inadequate to deal with them. The classification of big data becomes an important task in a wide variety of fields such as biomedicine, social media, marketing, etc. The recent advances in data gathering techniques have resulted in exponential growth of data. The characteristics of big data such as volume, diversity, and complexity make the analysis and knowledge extraction processes more complex. Thus standard data mining models need to be restructured to deal with this data. The main objective of this paper is to get deeper in big data classification and to compare various algorithms for the classification of big data including fuzzy and non-fuzzy algorithms. This paper also reviews some classification methods suitable for big data such as probabilistic classification, decision trees, rule-based methods, instance-based techniques, SVM methods, and neural networks.