Data Mining and Artificial Intelligence Techniques Used to Extract Big Data Patterns

A lot of research and analysis has been done that focuses on the implementation, use, and evaluation of artificial intelligence techniques. The analysis is done on different techniques and variations of known methods regarding their characteristics like speed, performance, and effectiveness using scientific methods, statistics and mathematical proofs. On the other end of the spectrum, a lot of research has been done on high-level data mining as well. The research on data mining usually stops at technical implementations and focuses mainly on high-level techniques to manipulate the bulk of data to be mined. The physical implementation is usually abstracted and left for libraries to optimize. In order to use this research in the area of big data, the areas of AI and Data mining need to be conjoined so that the appropriate knowledge from both technical and conceptual areas is used. The purpose of this literature review is to systematically review the research done on both the technical and conceptual ends of the spectrum and to find the overlapping techniques. This is needed to get a clear understanding of the entire knowledge extraction process from big data to business value. The research results in a broad view of all techniques and their appropriateness towards big data. In order to make decisions on the techniques used for a specific data mining problem, a broad view of all available solutions is needed. This paper attempts to deliver it by investigating all possibilities and discuss their advantages and disadvantages relating to big data.