Predicting paired preferences from sensory data

Buck, Dominic; Wakeling, Ian; Greenhoff, Keith; Hasted, Anne M.

doi:10.1016/s0950-3293(01)00041-6

Cited by 8 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to think about best-worst scaling is as an extension of paired comparisons (David, 1969;Thurstone, 1927), which is an established methodology in sensory and consumer science (e.g., Buck, Wakeling, Greenhoff, & Hasted, 2001;Duineveld, Arents, & King, 2000;Léon, Couronne, Marcuz, & Köster, 1999;Liem, Mars, & de Graaf, 2004). That methodology can be extended from choices among pairs to choices among larger sets of items, and best-worst scaling adds a further layer of sophistication by identifying not only the best item, but also the worst one.…”

Section: Theoretical Perspectivementioning

confidence: 99%

Best–worst scaling: An introduction and initial comparison with monadic rating for preference elicitation with food products

Jaeger

Jørgensen

Aaslyng

et al. 2008

Food Quality and Preference

120

View full text Add to dashboard Cite

Section: Theoretical Perspectivementioning

confidence: 99%

Best–worst scaling: An introduction and initial comparison with monadic rating for preference elicitation with food products

Jaeger

Jørgensen

Aaslyng

et al. 2008

Food Quality and Preference

120

View full text Add to dashboard Cite

“…An excellent survey of the use of this type of data in the food industry can be found in (Murray et al, 2001;Buck et al, 2001); for a Machine Learning perspective, see (Corney, 2002) and (Goyache et al, 2001;Del Coz et al 2004;Luaces et al 2004;Díez et al 2005).…”

Section: Sensory Data Analysismentioning

confidence: 99%

Clustering people according to their preference criteria

Díez

Coz

Luaces

et al. 2008

Expert Systems with Applications

View full text Add to dashboard Cite

Learning preferences is a useful task in application fields such as collaborative filtering, information retrieval, adaptive assistants or analysis of sensory data provided by panels. SVMs, using preference judgments, can induce ranking functions that map objects into real numbers, in such a way that more preferable objects achieve higher values. In this paper we present a new algorithm to build clusters of people with closely related tastes, and hence people whose preference judgment sets can be merged in order to learn more reliable ranking functions. In some application fields, these clusters can be seen as market segments that demand different kinds of products. The method proposed starts representing people's preferences in a metric space, where it is possible to define a kernel based similarity function; finally a clustering algorithm discovers significant groups with homogeneous tastes. The key point of our proposal is to use the ranking functions induced from the preference judgments of each person; we will show that those functions codify the criteria used by each person to decide her preferences. To illustrate the performance of our approach, we present two experimental cases. The first one deals with the collaborative filtering database EachMovie. The second database describes a real case of consumers of beef meat.

show abstract

“…As pointed out in (Cohen, Shapire, and Singer, 1999;Buck, Wakeling, Greenhoff, and Hasted, 2001), obtaining preference information may be easier and more natural than obtaining ratings. Moreover, if we represent consumer ratings by preference judgment pairs, we no longer need to assume that a rating of "7" means the same thing to every consumer in every session (Cohen et al, 1999).…”

Section: Regression and Preference Judgmentsmentioning

confidence: 99%