Probabilistic data mining model comparison

Patent metadata

Field	Value
Publication number	US-8990145-B2
Application number	US-201113214105-A
Country	US
Kind code	B2
Filing date	Aug 19, 2011
Priority date	Oct 5, 2010
Publication date	Mar 24, 2015
Grant date	Mar 24, 2015

Abstract

A first data mining model and a second data mining model are compared. A first data mining model M 1 represents results of a first data mining task on a first data set D 1 and provides a set of first prediction values. A second data mining model M 2 represents results of a second data mining task on a second data set D 2 and provides a set of second prediction values. A relation R is determined between said sets of prediction values. For at least a first record of an input data set, a first and second probability distribution is created based on the first and second data mining models applied to the first record. A distance measure d is calculated for said first record using the first and second probability distributions and the relation. At least one region of interest is determined based on said distance measure d.

First claim

The invention claimed is:

1. A method for comparing a first data mining model and a second data mining model, comprising:
providing a first data mining model M 1 representing results of a first data mining task on a first data set D 1 , wherein the first data mining model provides a set of first prediction values;
providing a second data mining model M 2 representing results of a second data mining task on a second data set D 2 , wherein the second data mining model provides a…

Assignees

• Lingenfelder Christoph
• Pompey Pascal
• Wurst Michael
• IBM

Inventors

• Lingenfelder Christoph
• Pompey Pascal
• Wurst Michael

Classifications

• G06F17/18 Primary

  Physics · mapped topic

• G06K9/62

  Physics · mapped topic

• G06F18/20

  Physics · mapped topic