Does Wikipedia Information Help Netflix Predictions?
Full Text:
icmla-20081003a.pdf
We explore several ways to estimate movie similarity
from the free encyclopedia Wikipedia with the goal of improving
our predictions for the Netflix Prize. Our system
first uses the content and hyperlink structure of Wikipedia
articles to identify similarities between movies. We then
predict a userâs unknown ratings by using these similarities
in conjunction with the userâs known ratings to initialize
matrix factorization and k-Nearest Neighbours algorithms.
We blend these results with existing ratings-based predictors.
Finally, we discuss our empirical results, which suggest
that external Wikipedia data does not significantly improve
the overall prediction accuracy.
Citation
J. Lees-Miller,
F. Anderson,
B. Hoehn,
R. Greiner.
"Does Wikipedia Information Help Netflix Predictions?".
International Conference on Machine Learning and Applications (ICMLA), December 2008.
Keywords: |
machine learning, netflix, collaborative filtering |
Category: |
In Conference |
BibTeX
@incollection{Lees-Miller+al:ICMLA08,
author = {John Lees-Miller and Fraser Anderson and Bret Hoehn and Russ
Greiner},
title = {Does Wikipedia Information Help Netflix Predictions?},
booktitle = {International Conference on Machine Learning and Applications
(ICMLA)},
year = 2008,
}
Last Updated: February 11, 2013
Submitted by Russ Greiner