57,233 Hits in 4.9 sec


Yuan Cao Zhang, Diarmuid Ó Séaghdha, Daniele Quercia, Tamas Jambor
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
Recommendation systems exist to help users discover content in a large body of items.  ...  We evaluate Auralist quantitatively over a broad set of metrics and, with a user study on music recommendation, show that Auralist's emphasis on serendipity indeed improves user satisfaction.  ...  This work was in part funded by RCUK through the Horizon Digital Economy Research grant (EP/G065802/1).  ... 
doi:10.1145/2124295.2124300 dblp:conf/wsdm/ZhangSQJ12 fatcat:ajzweapzfvaqvfbsqbxcxm763e

Integrating AHP and data mining for product recommendation based on customer lifetime value

Duen-Ren Liu, Ya-Yueh Shih
2005 Information & Management  
Product recommendation is a business activity that is critical in attracting customers.  ...  Accordingly, improving the quality of a recommendation to fulfill customers' needs is important in fiercely competitive environments.  ...  This research was supported in part by the National Science Council of the Republic of China under the grant NSC 92-2416-H-009-010.  ... 
doi:10.1016/ fatcat:thqisz7u6nfy3crzs5cqmuyy5q

Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics [article]

Tim Draws, Nava Tintarev, Ujwal Gadiraju, Alessandro Bozzon, Benjamin Timmermans
2020 arXiv   pre-print
However, this viewpoint diversity is not trivial to assess. In this paper we use existing and novel ranking fairness metrics to evaluate viewpoint diversity in search result rankings.  ...  This paper lays out important ground work for future research to measure and assess viewpoint diversity in real search result rankings.  ...  Acknowledgements This activity is financed by IBM and the Allowance for Top Consortia for Knowledge and Innovation (TKI's) of the Dutch ministry of economic affairs.  ... 
arXiv:2010.14531v1 fatcat:mivwonmrt5axpgvq6w5mx7tvzu

Hybrid approaches to product recommendation based on customer lifetime value and purchase preferences

Duen-Ren Liu, Ya-Yueh Shih
2005 Journal of Systems and Software  
Recommender systems have emerged in e-commerce applications to support the recommendation of products.  ...  Recommending products to attract customers and meet their needs is important in fiercely competitive environments.  ...  Acknowledgment This research was supported in part by the National Science Council of the Republic of China under the grant NSC 93-2416-H-009-011.  ... 
doi:10.1016/j.jss.2004.08.031 fatcat:j7mx47akdvfxpijtw4yz74jijq

Estimation of Fair Ranking Metrics with Incomplete Judgments [article]

Ömer Kırnap, Fernando Diaz, Asia Biega, Michael Ekstrand, Ben Carterette, Emine Yılmaz
2021 arXiv   pre-print
In order to address this problem, we propose a sampling strategy and estimation technique for four fair ranking metrics.  ...  However, the protected attributes of individuals are rarely present, limiting the application of fair ranking metrics in large scale systems.  ...  ) = 0 N + ℎ , if = 1 and ( ∈ D ) = 0 N ( , ) if = 0 and ( ∈ D ) = 1 N + ℎ + , if = 1 and ( ∈ D ) = 1 In effect, this process results in relevant documents having higher scores correlated to both system  ... 
arXiv:2108.05152v1 fatcat:yr6idob6lvdvpk2ptpvp3fx6ie

Improving recommendation lists through topic diversification

Cai-Nicolas Ziegler, Sean M. McNee, Joseph A. Konstan, Georg Lausen
2005 Proceedings of the 14th international conference on World Wide Web - WWW '05  
We introduce the intra-list similarity metric to assess the topical diversity of recommendation lists and the topic diversification approach for decreasing the intra-list similarity.  ...  In this work we present topic diversification, a novel method designed to balance and diversify personalized recommendation lists in order to reflect the user's complete spectrum of interests.  ...  Furthermore, we would like to thank all BookCrossing members participating in our online survey for devoting their time and giving us many invaluable comments.  ... 
doi:10.1145/1060745.1060754 dblp:conf/www/ZieglerMKL05 fatcat:jt7qa3ol4vawle62hc6t53op6m

Better Metrics for Ranking SE Researchers [article]

George Mathew, Tim Menzies
2018 arXiv   pre-print
Using PR_W, we offer a ranking of the top 20 SE authors in the last decade.  ...  This paper studies how SE researchers are ranked using a variety of metrics and data from 35,406 authors of 35,391 papers from 34 top SE venues in the period 1992-2016.  ...  Using that stable ranking, we offer a ranking of the top-20 SE authors in the last decade.  ... 
arXiv:1805.12124v1 fatcat:3ocphlvlk5h2vcigtcst43nexm

Precision-oriented evaluation of recommender systems

Alejandro Bellogin, Pablo Castells, Ivan Cantador
2011 Proceedings of the fifth ACM conference on Recommender systems - RecSys '11  
In our experiments with three state-of-the-art recommenders, four of the evaluation methodologies are consistent with each other and differ from error metrics, in terms of the comparative recommenders'  ...  There is considerable methodological divergence in the way precision-oriented metrics are being applied in the Recommender Systems field, and as a consequence, the results reported in different studies  ...  Acknowledging this, recent works evaluate top-N ranked recommendation lists with precision-based metrics [2, 8, 5, 1] , drawing from well-studied methodologies in the Information Retrieval (IR) field.  ... 
doi:10.1145/2043932.2043996 dblp:conf/recsys/BelloginCC11 fatcat:hhrdrmpfj5fdto2mzriorkzgqy

A Generic Top-N Recommendation Framework For Trading-off Accuracy, Novelty, and Coverage [article]

Zainab Zolaktaf, Reza Babanezhad, Rachel Pottinger
2018 arXiv   pre-print
Standard collaborative filtering approaches for top-N recommendation are biased toward popular items.  ...  Our framework also enables personalization of existing non-personalized algorithms, making them competitive with existing personalized algorithms in key performance metrics, including accuracy and coverage  ...  This work has been funded by NSERC Canada, and supported in part by the Institute for Computing, Information and Cognitive Systems at UBC.  ... 
arXiv:1803.00146v1 fatcat:pidntp42kjbuhfccpzpmqij3qi

Exploring Gender Distribution in Music Recommender Systems

Dougal Shakespeare, Lorenzo Porcaro, Emilia Gómez
2020 Zenodo  
Whilst accuracy metrics have been widely applied to evaluate recommendations in mRS literature, evaluating a user's item utility from other impact-oriented perspec-tives, including their potential for  ...  To assess group biases introduced by CF, we deploy a recently proposed metric of bias disparity on two listening event datasets: the LFM-1b dataset, and the earlier constructed Celma's dataset.  ...  Globally, we can then compute P @K by averaging over P u @K all users in T . Mean average precision at top K recommendations (MAP@K) is a rank based metric to assess the accuracy of a recommendation.  ... 
doi:10.5281/zenodo.4091510 fatcat:5ug2dprnr5haxgfukjtpofnlxe


Yue Shi, Alexandros Karatzoglou, Linas Baltrunas, Martha Larson, Alan Hanjalic
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
If accurate top-N recommendation lists are to be produced for such graded relevance domains, it is critical to generate a ranked list of recommended items directly rather than predicting ratings.  ...  The model optimizes for Graded Average Precision, a metric that has been proposed recently for assessing the quality of ranked results list for graded relevance.  ...  As mentioned in Section 1, even results that are ranked optimally in terms of NDCG may still yield suboptimal top-N recommendations.  ... 
doi:10.1145/2505515.2505653 dblp:conf/cikm/ShiKBLH13 fatcat:4vsr343swzf35mydj2q57mpzui

Rank and relevance in novelty and diversity metrics for recommender systems

Saúl Vargas, Pablo Castells
2011 Proceedings of the fifth ACM conference on Recommender systems - RecSys '11  
Furthermore, the metrics reported so far miss important properties such as taking into consideration the ranking of recommended items, or whether items are relevant or not, when assessing the novelty and  ...  The Recommender Systems community is paying increasing attention to novelty and diversity as key qualities beyond accuracy in real recommendation scenarios.  ...  The diversifiers re-rank the top n recommended items (n = 500 in our experiment) returned by a baseline recommender, by greedily optimizing an objective function.  ... 
doi:10.1145/2043932.2043955 fatcat:byrroapfazajxjywcfjh7d5dbe

Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols

Pedro G. Campos, Fernando Díez, Iván Cantador
2013 User modeling and user-adapted interaction  
The analysis show that meaningful divergences appear in the evaluation protocols used-metrics and methodologies.  ...  Campos et al. conditions yield to remarkably distinct performance and relative ranking values of the recommendation approaches.  ...  Note that, in general, rating prediction accuracy metrics are used to assess a rating prediction task, while ranking precision metrics are used to assess a top-N recommendation task.  ... 
doi:10.1007/s11257-012-9136-x fatcat:uygawlf53jh7ndy2lrp4q3lntm

Lightweight Collaborative Filtering Method for Binary-Encoded Data [chapter]

Sholom M. Weiss, Nitin Indurkhya
2001 Lecture Notes in Computer Science  
Because the data are binary (true-or-false) encoded, and not ranked preferences on a numerical scale, e cient a n d lightweight s c hemes are described for compactly storing data, computing similarities  ...  Examples of transactions that can be described in this manner are items purchased by customers or web pages visited by individuals.  ...  The R-metric is e ective in measuring performance over a ranked list of recommendations.  ... 
doi:10.1007/3-540-44794-6_40 fatcat:vkqfds5gvfgedlawdfpjndqdze

Recommending Given Names [article]

Folke Mitzlaff, Gerd Stumme
2013 arXiv   pre-print
The present work tackles the problem of recommending given names, by firstly mining for inter-name relatedness in data from the Social Web.  ...  We also show, how the gathered inter-name relationships can be used for meaningful result diversification of PageRank-based recommendation systems.  ...  For the nearest neighbor approach, only the top N similar users to u are considered in the summation.  ... 
arXiv:1302.4412v2 fatcat:kzw4ppgwcbf6ji2edkccjv2iiu
« Previous Showing results 1 — 15 out of 57,233 results