[DB] Data Mining: Definition, Software

Data Mining Definition

1

Data mining is the process exploration and analysis, by automatic or semi-automatic means, of large quantities of data in order to discover meaningful patterns and rules.

- Berry and Linoff, 1997(Data Mining Techniques. New York: Wiley)

later, Berry & Linoff regretted the 1997 reference(the underlined sentence).

they expanded the role of data exploration and analysis. like the following,

To expand further, there are six types of activities that can be done using data mining.

....

Data clustering is one of the six essential tasks of data mining, which aims to discover useful information by exploring and analyzing large amounts of data.

- Berry and Linoff, 2000(Mastering Data Mining. New York: Wiley)

▼ 

The six essential tasks of data mining.

Direct DM: Classification, Estimation, Prediction

Indirect DM: Clustering, Association Rules, Description and Visualization

2

(Data mining is) Extracting useful information from large data sets.

- Handm D., Mannila, H. and Smythm p. (2001). Principles of Data Mining. Cambridge, MA: MIT Press.

3

(Data mining is) The process of discovering meaningful correlations, patterns and trends by sifting through large amounts of data stored in repositories. Data mining employs pattern recognition technologies, as well as statistical and mathematical techniques.

- Gartner Group (http://www.gartner.com/it-glossary/data-mining, May 14, 2010)

Data Mining Software

IBM - Intelligent Miner

MS - SQL Server 2005

Oracle - Data Mining

Teradata - Warehouse Miner

SAS - Enterprise Miner

IBM - SPSS Modeler

R(open source)