Big Data Analytics
Big Data is a popular buzzword, which rather stands for the neat application of Data Mining (=analytics part) methods to extraordinary big data sets (=big data part).
But the craftsmanship does not only lie in the handling of big data sets. Even more important is the proper selection of the right data with respect to content and size. In the ideal case that way it does not even come to oversized and unnecessarily expensive data while still maintaining the full benefit of the data and example based approach.
ANDATA believes in an integral procedure, where the topics "data" and "analytics" are not approached sequentially and separately but in an integral and iterative approach. The data mining methods are used in an early stage for the specification and controlled expansion of the data base. Thus one can be sure, that no unnecessary and expensive data graves are produced. Instead exactly the right data with respect to content and size are gathered, which is needed for a valid modeling and decision support.