Recommender systems make product suggestions that are tailored to the user's individual needs and represent powerful means to combat information overload. In this paper, we focus on the item prediction task of Recommender Systems and present SwarmRankCF, a method to automatically optimize the performance quality of recommender systems using a Swarm Intelligence perspective. Our approach, which is well-founded in a Particle Swarm Optimization framework, learns a ranking function by optimizing the combination of unique characteristics (i.e., features) of users, items and their interactions. In particular, we build feature vectors from a factorization of the user-item interaction matrix, and directly optimize Mean Average Precision metric in order to learn a linear ranking model for personalized recommendations. Our experimental evaluation, on a real world online radio dataset, indicates that our approach is able to find ranking functions that significantly improve the performance of the system for the Top-N recommendation task.
%0 Conference Paper
%1 Diaz-Aviles:2012:SRR:2365952.2366001
%A Diaz-Aviles, Ernesto
%A Georgescu, Mihai
%A Nejdl, Wolfgang
%B Proceedings of the sixth ACM conference on Recommender systems
%C New York, NY, USA
%D 2012
%I ACM
%K 2012 collaborative_filtering information_filtering matrix_factorization myown pso recommender_systems recsys recsys2012 swarm_intelligence
%P 229--232
%R 10.1145/2365952.2366001
%T Swarming to rank for recommender systems
%U http://doi.acm.org/10.1145/2365952.2366001
%X Recommender systems make product suggestions that are tailored to the user's individual needs and represent powerful means to combat information overload. In this paper, we focus on the item prediction task of Recommender Systems and present SwarmRankCF, a method to automatically optimize the performance quality of recommender systems using a Swarm Intelligence perspective. Our approach, which is well-founded in a Particle Swarm Optimization framework, learns a ranking function by optimizing the combination of unique characteristics (i.e., features) of users, items and their interactions. In particular, we build feature vectors from a factorization of the user-item interaction matrix, and directly optimize Mean Average Precision metric in order to learn a linear ranking model for personalized recommendations. Our experimental evaluation, on a real world online radio dataset, indicates that our approach is able to find ranking functions that significantly improve the performance of the system for the Top-N recommendation task.
%@ 978-1-4503-1270-7
@inproceedings{Diaz-Aviles:2012:SRR:2365952.2366001,
abstract = {Recommender systems make product suggestions that are tailored to the user's individual needs and represent powerful means to combat information overload. In this paper, we focus on the item prediction task of Recommender Systems and present SwarmRankCF, a method to automatically optimize the performance quality of recommender systems using a Swarm Intelligence perspective. Our approach, which is well-founded in a Particle Swarm Optimization framework, learns a ranking function by optimizing the combination of unique characteristics (i.e., features) of users, items and their interactions. In particular, we build feature vectors from a factorization of the user-item interaction matrix, and directly optimize Mean Average Precision metric in order to learn a linear ranking model for personalized recommendations. Our experimental evaluation, on a real world online radio dataset, indicates that our approach is able to find ranking functions that significantly improve the performance of the system for the Top-N recommendation task.},
acmid = {2366001},
added-at = {2012-12-07T17:28:53.000+0100},
address = {New York, NY, USA},
author = {Diaz-Aviles, Ernesto and Georgescu, Mihai and Nejdl, Wolfgang},
biburl = {https://www.bibsonomy.org/bibtex/2efc3339e48ac3cd9e298506a17d419cc/diaz.l3s.de},
booktitle = {Proceedings of the sixth ACM conference on Recommender systems},
description = {Swarming to rank for recommender systems},
doi = {10.1145/2365952.2366001},
interhash = {cd17ec3202489d0eb98bde5cceb23bfc},
intrahash = {efc3339e48ac3cd9e298506a17d419cc},
isbn = {978-1-4503-1270-7},
keywords = {2012 collaborative_filtering information_filtering matrix_factorization myown pso recommender_systems recsys recsys2012 swarm_intelligence},
location = {Dublin, Ireland},
numpages = {4},
pages = {229--232},
publisher = {ACM},
series = {RecSys '12},
timestamp = {2012-12-07T17:28:53.000+0100},
title = {Swarming to rank for recommender systems},
url = {http://doi.acm.org/10.1145/2365952.2366001},
year = 2012
}