A recommender system based on the collaborative behavior of bird flocks

Esin Saka; Olfa Nasraoui

6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing

Research Article

A recommender system based on the collaborative behavior of bird flocks

Download206 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/icst.collaboratecom.2010.11,
    author={Esin Saka and Olfa Nasraoui},
    title={A recommender system based on the collaborative behavior of bird flocks},
    proceedings={6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing},
    publisher={IEEE},
    proceedings_a={COLLABORATECOM},
    year={2011},
    month={5},
    keywords={Swarm intelligence recommender system collaborative filtering flocks of agents bird flocks},
    doi={10.4108/icst.collaboratecom.2010.11}
}

Esin Saka
Olfa Nasraoui
Year: 2011
A recommender system based on the collaborative behavior of bird flocks
COLLABORATECOM
ICST
DOI: 10.4108/icst.collaboratecom.2010.11

Esin Saka¹^,*, Olfa Nasraoui¹^,*

1: Knowledge Discovery and Web Mining Lab, University of Louisville, Louisville, KY, USA

*Contact email: esin.saka@louisville.edu, olfa.nasraoui@louisville.edu

Abstract

This paper proposes a swarm intelligence based recommender system (FlockRecom) based on the collaborative behavior of bird flocks for generating Top-N recommendations. The flock-based recommender algorithm (FlockRecom) iteratively adjusts the position and speed of dynamic flocks of agents on a visualization panel. By using the neighboring agents on the visualization panel, top-n recommendations are generated. The performance of FlockRecom is evaluated using the Jester Dataset-2 and is compared with a traditional collaborative filtering based recommender system. Experiments on real data illustrate the workings of the recommender system and its advantages over its CF baseline.

Keywords: Swarm intelligence recommender system collaborative filtering flocks of agents bird flocks

Published: 2011-05-12
Publisher: IEEE

: http://dx.doi.org/10.4108/icst.collaboratecom.2010.11