University Homepage School Homepage School Contacts School Search

 

Data Preparation

Data preparation is a crucial stage in every data mining project. According to Pyle (Data preparation for data mining, p. 11), it takes up 60% of the total time of every data mining project (different figures can be found in different textbooks, but everyone agrees that it is important and time-consuming).

• A general overview of the data preparation process
• Data transformations
• Data reduction. Some people consider data reduction as a part of data preparation. Others see it as a separate step before or after data preparation. Any material concerning data reduction can be found in the pages about large datasets.

fuzzy/probabilistic matching, fuzzy merge, ... http://www.sconsig.com/tip00219.htm