I have a contact table and a customer table. The two tables will contain columns like
First name
Last Name,
Date of Birth
Post Code,
House Number
Street Name
etc.
I would like to find the different combinations in which I can relate the customer and contact data.
Like its is possible that the first name and last name are same but date of birth is different. This indicates that the contact and customer is the same. Now I do not know these combinations and I would like to have this set generated for me.
From Integration Service (Sql Server 2005) I get the data and I would like to know the patterns in which data will differ. Is there any way of achieving this?
I am very new to Data Mining and would like to have some direction as to how to progress with this.
The fuzzy match functionality in Integration Services is a better solution for this problem.
Data Mining requires a training set that already has the patterns you wish to discover - once you train a mining model with that data set, you can then apply those patterns to new data and predict missing information (potentially, depending on the type of algorithm you use to build the model).
No comments:
Post a Comment