I want to know about the different forms of KDD in data mining

In case anyone else is wondering, KDD is "Knowledge Discovery in Databases". It's a new one on me.

http://www2.cs.uregina.ca/~dbd/cs831/notes/kdd/1_kdd.html

I have heard of it before but I have never done any myself.

Theres 3 main approaches to my knowledge, Association, Classification and Clustering, the latter is somewhat random depending on the algorithm.

 

Heres a link for more info http://www.ibm.com/developerworks/library/ba-data-mining-techniques/

 

Heres a link for some open source software http://www.borgelt.net/software.html

 

What specifically do you want to know? Pattern recognition is quite a common topic in data mining.

 

A little more data https://en.wikipedia.org/wiki/Association_rule_learning

Edited November 21, 201510 yr by DevilSolution

http://guidetodatamining.com/assets/guideChapters/Guide2DataMining.pdf

 

Is a free ebook providing an insight into data mining using python. It focuses on how companies make recommendations on what somebody will like based on choices other people have made who are similar for them. For example if person A&B both bought the whole harry potter series and person C has bought a number of harry potter books we could make the recommendation that person C might like to read the rest of the harry potter books.

 

http://infolab.stanford.edu/~ullman/mmds.html

 

Takes a statistical approach to data mining and looks at instances of cholera on a map and attempts to establish a relationship between them for instance they were all in a similar area.