Big Data Analytics for Disparate Data

Abstract

Disparate data is heterogeneous data with variety in data formats, diverse data dimensionality, and low quality. Missing values, inconsistencies, ambiguous records, noise, and high data redundancy contribute to the ‘low quality’ of disparate data. It is a challenge to integrate disparate data from various sources. Big data is often disparate, dynamic, untrustworthy, and inter-related. Big Data analytics can be used to analyze correlation between factors and detect patterns or uncover unknown trends in disparate data. This paper introduces quality problems of disparate data. Some methods and technology progress regarding Big Data analytics for disparate data are presented. Challenges of Big Data analytics in dealing with disparate data are also discussed in this paper.