ABSTRACT

This chapter explores the process behind big data and suggests that approaches for formally analyzing it. Corporations and governments are increasingly interested in acquiring, storing, transmitting, and eventually analyzing the mix of telephone call data, email packets, short message texts, pictures, videos, audios, and all various forms of social media. Big data can come in multiple forms—from highly structured financial data, text files, multimedia files, and the variety of media types employed by social media. A high volume of data is the most consistent characteristic of big data. Time series techniques allow forecasting of the data by isolating and projecting the patterns of past data into the future. Clustering and decision tree analysis are methods often used in the early exploratory analysis of the data. Clustering is a popular method used to form homogeneous groups of like subjects within a data set based on their internal structure.