Model-Based Learning from Preference Data

Liu, Qinghua; Crispino, Marta; Scheel, Ida; Vitelli, Valeria; Frigessi, Arnoldo

doi:10.1146/annurev-statistics-031017-100213

Cited by 23 publications

(19 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For more details of these models and their applications, see D. E. Critchlow et al (1991), Marden (1996), Alvo and Yu (2014), and Q. Liu, Crispino, Scheel, Vitelli, and Frigessi (2019).…”

Section: Discussionmentioning

confidence: 99%

“…Other rank aggregation methods not considered here are online rank aggregation (Helmbold & Warmuth, ; Yasutake, Hatano, Takimoto, & Takeda, ), robust rank aggregation methods (Kolde, Laur, Adler, & Vilo, ), top‐ K aggregation from multiple omics ranked lists (Schimek et al, ), and an indirect inference approach for rank aggregation (Švendová & Schimek, ). For comparison of various aggregation methods, see Li, Wang, and Xiao (); Q. Liu et al ().…”

Section: Rank Aggregation Methodsmentioning

confidence: 99%

“…As some of them could belong to more than one class, Table gives a summary of these models and lists out whether they allow for the presence of covariates, whether they can handle big ranking data with a large number of items (says greater than 15) as well as incomplete rankings. For more details of these models and their applications, see D. E. Critchlow et al (), Marden (), Alvo and Yu (), and Q. Liu, Crispino, Scheel, Vitelli, and Frigessi ().…”

Section: Probability Models For Ranking Datamentioning

confidence: 99%

See 2 more Smart Citations

Analysis of ranking data

2019

WIREs Computational Stats

View full text Add to dashboard Cite

Ranking is one of the simple and efficient data collection techniques to understand individuals' perception and preferences for some items such as products, people, and species. Ranking data are frequently collected when individuals are asked to rank a set of items according to a certain preference criterion. Over the years, many statistical models and methods have been developed for analyzing ranking data. This paper will give a literature review of these models and methods and present the recent advances of the analysis of ranking data. This article is categorized under: Statistical and Graphical Methods of Data Analysis > Nonparametric Methods

show abstract

“…For more details of these models and their applications, see D. E. Critchlow et al (1991), Marden (1996), Alvo and Yu (2014), and Q. Liu, Crispino, Scheel, Vitelli, and Frigessi (2019).…”

Section: Discussionmentioning

confidence: 99%

Section: Rank Aggregation Methodsmentioning

confidence: 99%

Section: Probability Models For Ranking Datamentioning

confidence: 99%

See 1 more Smart Citation

Analysis of ranking data

2019

WIREs Computational Stats

View full text Add to dashboard Cite

show abstract

“…In this section we give the background for understanding the functions in the BayesMallows package. More details can be found in Vitelli et al (2018) and Liu et al (2019). The section is organized as follows: we first clarify the notations that we will use throughout the paper (Section 2.1).…”

Section: Background: the Bayesian Mallows Model For Rankingsmentioning

confidence: 99%

BayesMallows: An R Package for the Bayesian Mallows Model

Sørensen¹,

Crispino²,

Liu³

et al. 2020

The R Journal

Self Cite

View full text Add to dashboard Cite

BayesMallows is an R package for analyzing preference data in the form of rankings with the Mallows rank model, and its finite mixture extension, in a Bayesian framework. The model is grounded on the idea that the probability density of an observed ranking decreases exponentially with the distance to the location parameter. It is the first Bayesian implementation that allows wide choices of distances, and it works well with a large amount of items to be ranked. BayesMallows handles non-standard data: partial rankings and pairwise comparisons, even in cases including non-transitive preference patterns. The Bayesian paradigm allows coherent quantification of posterior uncertainties of estimates of any quantity of interest. These posteriors are fully available to the user, and the package comes with convienient tools for summarizing and visualizing the posterior distributions.

show abstract

“…Possible choices of distance functions include the footrule distance, the Spearman distance, and the Kendall distance. In this paper, we choose the footrule distance, defined as d(r, ρ) = n i=1 |r i − ρ i |, because of its effectiveness [17]. Other distances can also be used.…”

Section: Bayesian Mallows For Clicking Data (Bmcd)mentioning

confidence: 99%

Diverse personalized recommendations with uncertainty from implicit preference data with the Bayesian Mallows model

Liu

Reiner

Frigessi

et al. 2019

Knowledge-Based Systems

Self Cite

View full text Add to dashboard Cite

Clicking data, which exists in abundance and contains objective user preference information, is widely used to produce personalized recommendations in web-based applications. Current popular recommendation algorithms, typically based on matrix factorizations, often have high accuracy and achieve good clickthrough rates. However, diversity of the recommended items, which can greatly enhance user experiences, is often overlooked. Moreover, most algorithms do not produce interpretable uncertainty quantifications of the recommendations. In this work, we propose the Bayesian Mallows for Clicking Data (BMCD) method, which augments clicking data into compatible full ranking vectors by enforcing all the clicked items to be top-ranked. User preferences are learned using a Mallows ranking model. Bayesian inference leads to interpretable uncertainties of each individual recommendation, and we also propose a method to make personalized recommendations based on such uncertainties. With a simulation study and a real life data example, we demonstrate that compared to state-of-the-art matrix factorization, BMCD makes personalized recommendations with similar accuracy, while achieving much higher level of diversity, and producing interpretable and actionable uncertainty estimation.

show abstract

Model-Based Learning from Preference Data

Cited by 23 publications

References 46 publications

Analysis of ranking data

Analysis of ranking data

BayesMallows: An R Package for the Bayesian Mallows Model

Diverse personalized recommendations with uncertainty from implicit preference data with the Bayesian Mallows model

Contact Info

Product

Resources

About