Hi
I am using unduplicate independent match specification for identifying unique customers.
i have given high negative weight over-rides on few column but still the output is not coming as expected.
Has any1 some idea of how m-prob and u-prob affect the agreement and disagreemnet weight for the matching columns. Does this thing supersede the weight over-rides?
Thanks in advance!
How to increase the disagreement weight in matching
-
- Participant
- Posts: 54607
- Joined: Wed Oct 23, 2002 10:52 pm
- Location: Sydney, Australia
- Contact:
Weight overrides supersede the agreement/disagreement weights calculated using m-prob and u-prob. (That's why they're called overrides.)
"Not coming as expected" is singularly unhelpful to diagnosis. You will need to be much more specific, particularly in regard to precisely how you set things up, expected and actual results.
"Not coming as expected" is singularly unhelpful to diagnosis. You will need to be much more specific, particularly in regard to precisely how you set things up, expected and actual results.
IBM Software Services Group
Any contribution to this forum is my own opinion and does not necessarily reflect any position that IBM may hold.
Any contribution to this forum is my own opinion and does not necessarily reflect any position that IBM may hold.