searching data mining tool that detects repeating patterns

[stretch1]

I’m looking for a Data Mining tool that detects repeating patterns in data and if found make groups of it.

Example: Customer John Doe buys a red Dodge with airco and leather seats, customer Jane Doe buys also this car with the same characteristics. One can call a red Dodge with airco and leather seats a resource connected to a customer, but as there are multiple customers connected to this resource we want to create a group for it and connect the customers John and Jane Doe to the group.

Anyone aware of such a data mining tool?
Thanks.

 

[Predictor]

I suppose association rule analysis (also called "market basket analysis") might work. You can find a list of commercial and free tools which perform such analysis at:

http://www.kdnuggets.com/software/associations.html

If, however, you know how the groups will be defined (model, color, A/C, seat type_, then you might be able to just perform simple database queries, grouping on these items and sorting groups by size, so that the most common combinations of these attributes are apparent.


Good luck,
Will

http://matlabdatamining.blogspot.com/