Local Utility Elicitation in

Generalized Additive Independent (GAI) Models

Abstract

Structured utility models are essential for the effective representation and elicitation of complex multiattribute utility functions. Generalized additive independence (GAI) models provide an attractive structural model of user preferences, offering a balanced tradeoff between simplicity and applicability. While representation and inference with such models is reasonably well understood, elicitation of the parameters of such models has been studied less from a practical perspective. We propose a procedure to elicit "local" utility information that can be used to fill in a GAI model, rather than relying on "global" queries. Our local utility queries take full advantage of GAI structure and provide a sound framework for extending the elicitation procedure to settings where the uncertainty over utility parameters is represented probabilistically. We describe experiments using a myopic value-of-information approach to elicitation in a large GAI model.

In proceedings of the 21st Conference on Uncertainty in Artificial Intelligence (UAI-05), Edinburgh, 2005.

@inproceedings{BraziunasBoutilier-UAI05,
author = "Darius Braziunas and Craig Boutilier",
title = "Local Utility Elicitation in {GAI} Models",
booktitle = "Proceedings of the Twenty-first Conference on
             Uncertainty in Artificial Intelligence",
address = "Edinburgh",
pages = "42--49",
year = "2005"}