Data mining booknote

Data mining takes advantage of advances in the fields of artificial intelligence (AI) and statistics.Both disciplines have been working on problems of pattern recognition and classification. Both communities have made great contributions to the understanding and application of neural nets and decision trees.

1. Describe the Data
        explore data, select data, cleanse the data,and classify data.
 
2. Build Predictive Model
          I. use sample data to build a predictive model (based on patterns with known results)
         II. use data outside the sample to test the veracity of the model
        III. empirically verify the model by applying model to customer's database

3.  Data Mining's DONTS
        I. It doesn't uncover solution automatically, and the patterns uncovered must be verified to
            the reality.
       II. the predictive uncovered patterns are NOT necessarily the CAUSES of the behaviors.
      III. you must understand your data,

4. Data mining does not replace skilled business analysts but confirm their empirical observations
   and find new, subtle patterns that yield steady incremental improvement (plus the occasional
   breakthrough insight).


Application:
    Detect Fraud:  Telecommunication, Credit Card Company, Insurance Company, and Stock
                          Exchange Company.


   Medical effective test


   Retailer





     









source: http://www.twocrows.com/intro-dm.pdf