Skip navigation

Economical Active Feature-value Acquisition through Expected Utility Estimation

Authors: Melville, Prem
Saar-Tsechansky, Maytal
Mooney, Raymond
Provost, Foster
Keywords: machine learning;data mining;active learning;cost-sensitive learning
Issue Date: Aug-2005
Publisher: IEEE Computer Society
Citation: Proceedings of the KDD-05 Workshop on Utility-Based Data Mining,
Series/Report no.: CeDER-PP-2005-05
Abstract: In many classification tasks training data have missing feature values that can be acquired at a cost. For building accurate predictive models, acquiring all missing values is often prohibitively expensive or unnecessary, while acquiring a random subset of feature values may not be most effective. The goal of active feature-value acquisition is to incrementally select feature values that are most cost-effective for improving the model’s accuracy. We present two policies, Sampled Expected Utility and Expected Utility-ES, that acquire feature values for inducing a classification model based on an estimation of the expected improvement in model accuracy per unit cost. A comparison of the two policies to each other and to alternative policies demonstrate that Sampled Expected Utility is preferable as it effectively reduces the cost of producing a model of a desired accuracy and exhibits a consistent performance across domains.
Appears in Collections:CeDER Published Papers

Files in This Item:
File Description SizeFormat 
CPP-05-05.pdf103.47 kBAdobe PDFView/Open

Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.