Peters, Markus, Saar-Tsechansky, Maytal, Ketter, Wolfgang ORCID: 0000-0001-9008-142X, Williamson, Sinead A., Groot, Perry and Heskes, Tom ORCID: 0000-0002-3398-5235 (2018). A scalable preference model for autonomous decision-making. Mach. Learn., 107 (6). S. 1039 - 1069. DORDRECHT: SPRINGER. ISSN 1573-0565

Full text not available from this repository.

Abstract

Emerging domains such as smart electric grids require decisions to be made autonomously, based on the observed behaviors of large numbers of connected consumers. Existing approaches either lack the flexibility to capture nuanced, individualized preference profiles, or scale poorly with the size of the dataset. We propose a preference model that combines flexible Bayesian nonparametric priors-providing state-of-the-art predictive power-with well-justified structural assumptions that allow a scalable implementation. The Gaussian process scalable preference model via Kronecker factorization (GaSPK) model provides accurate choice predictions and principled uncertainty estimates as input to decision-making tasks. In consumer choice settings where alternatives are described by few key attributes, inference in our model is highly efficient and scalable to tens of thousands of choices.

Item Type: Journal Article
Creators:
CreatorsEmailORCIDORCID Put Code
Peters, MarkusUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Saar-Tsechansky, MaytalUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Ketter, WolfgangUNSPECIFIEDorcid.org/0000-0001-9008-142XUNSPECIFIED
Williamson, Sinead A.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Groot, PerryUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Heskes, TomUNSPECIFIEDorcid.org/0000-0002-3398-5235UNSPECIFIED
URN: urn:nbn:de:hbz:38-185657
DOI: 10.1007/s10994-018-5705-5
Journal or Publication Title: Mach. Learn.
Volume: 107
Number: 6
Page Range: S. 1039 - 1069
Date: 2018
Publisher: SPRINGER
Place of Publication: DORDRECHT
ISSN: 1573-0565
Language: English
Faculty: Unspecified
Divisions: Unspecified
Subjects: no entry
Uncontrolled Keywords:
KeywordsLanguage
Computer Science, Artificial IntelligenceMultiple languages
Refereed: Yes
URI: http://kups.ub.uni-koeln.de/id/eprint/18565

Downloads

Downloads per month over past year

Altmetric

Export

Actions (login required)

View Item View Item