METHOD FOR CONSTRUCTING SEGMENTATION-BASED PREDICTIVE MODELS
First Claim
1. A method for a process performed on a computer for training multivariate segment model objects, the method comprising:
- 1) accessing a collection of training data records comprising examples of input values that are available to a multivariate segment model object, together with corresponding desired output value(s) that the multivariate segment model is intended to predict;
2) presenting the training data records to the multivariate segment model object by calling one or more scan-data-record interface functions, wherein the segment model object responds by generating and pruning pluralities of data segments and associated segment models, at least one of which comprises a multivariate segment model; and
3) repeating said accessing and said presenting until the multivariate segment model object indicates that it does not need to have the training records presented over again.
3 Assignments
0 Petitions
Accused Products
Abstract
The present invention generally relates to computer databases and, more particularly, to data mining and knowledge discovery. The invention specifically relates to a method for constructing segmentation-based predictive models, such as decision-tree classifiers, wherein data records are partitioned into a plurality of segments and separate predictive models are constructed for each segment. The present invention contemplates a computerized method for automatically building segmentation-based predictive models that substantially improves upon the modeling capabilities of decision trees and related technologies, and that automatically produces models that are competitive with, if not better than, those produced by data analysts and applied statisticians using traditional, labor-intensive statistical techniques. The invention achieves these properties by performing segmentation and multivariate statistical modeling within each segment simultaneously. Segments are constructed so as to maximize the accuracies of the predictive models within each segment. Simultaneously, the multivariate statistical models within each segment are refined so as to maximize their respective predictive accuracies.
-
Citations
3 Claims
-
1. A method for a process performed on a computer for training multivariate segment model objects, the method comprising:
-
1) accessing a collection of training data records comprising examples of input values that are available to a multivariate segment model object, together with corresponding desired output value(s) that the multivariate segment model is intended to predict; 2) presenting the training data records to the multivariate segment model object by calling one or more scan-data-record interface functions, wherein the segment model object responds by generating and pruning pluralities of data segments and associated segment models, at least one of which comprises a multivariate segment model; and 3) repeating said accessing and said presenting until the multivariate segment model object indicates that it does not need to have the training records presented over again. - View Dependent Claims (2, 3)
-
Specification