Corpus ID: 51822041

The Netflix Prize - and SVD

@inproceedings{Gower2014TheNP,
  title={The Netflix Prize - and SVD},
  author={Stephen A. Gower},
  year={2014}
}
  • Stephen A. Gower
  • Published 2014
  • Singular Value Decompositions (SVD) have become very popular in the field of Collaborative Filtering. The winning entry for the famed Netflix Prize had a number of SVD models including SVD++ blended with Restricted Boltzmann Machines. Using these methods they achieved a 10 percent increase in accuracy over Netflix’s existing algorithm. In this paper I explore the different facets of a successful recommender model. I also will explore a few of the more prominent SVD based models such as… CONTINUE READING

    Figures from this paper.

    Recommender Systems in Light of Big Data
    • 8
    Predicting Drugs Adverse Side-Effects Using a Recommender-System
    • 2
    • Highly Influenced
    • PDF
    Embedding and latent variable models using maximal correlation
    • 1
    Media content personalisation brokerage platform
    • 2
    Entrywise convergence of iterative methods for eigenproblems
    Mining place-time affinity to improve POI recommendation

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 10 REFERENCES
    Restricted Boltzmann machines for collaborative filtering
    • 1,529
    • PDF
    Eigentaste: A Constant Time Collaborative Filtering Algorithm
    • 1,449
    • PDF
    Improving regularized singular value decomposition for collaborative filtering
    • 654
    • PDF
    The BellKor Solution to the Netflix Grand Prize
    • 421
    • PDF
    Applying SVD on Generalized Item-based Filtering
    • 22
    • Highly Influential
    • PDF
    Matrix Factorization Techniques for Recommender Systems
    • 2,675
    • Highly Influential
    Jahrer, The BigChaos Solution to the Netflix Grand Prize
    • 2009
    The Pragmatic Theory Solution to the Netflix Grand Prize
    • 2009