Addressing Item-Cold Start Problem in Recommendation Systems using Model Based Approach and Deep Learning

@inproceedings{Obadic2017AddressingIS,
  title={Addressing Item-Cold Start Problem in Recommendation Systems using Model Based Approach and Deep Learning},
  author={Ivica Obadic and Gjorgji Madjarov and I. Dimitrovski and D. Gjorgjevikj},
  booktitle={ICT Innovations},
  year={2017}
}
  • Ivica Obadic, Gjorgji Madjarov, +1 author D. Gjorgjevikj
  • Published in ICT Innovations 2017
  • Engineering, Computer Science, Mathematics
  • Traditional recommendation systems rely on past usage data in order to generate new recommendations. [...] Key Method In particular, we use latent factor model for recommendation, and predict the latent factors from item’s descriptions using convolutional neural network when they cannot be obtained from usage data. Latent factors obtained by applying matrix factorization to the available usage data are used as ground truth to train the convolutional neural network.Expand Abstract

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES
    Deep content-based music recommendation
    • 767
    • PDF
    Factorization meets the neighborhood: a multifaceted collaborative filtering model
    • 2,803
    • PDF
    Scalable Collaborative Filtering with Jointly Derived Neighborhood Interpolation Weights
    • 507
    • PDF
    A Convolutional Neural Network for Modelling Sentences
    • 2,358
    • PDF
    Programming Collective Intelligence
    • 231
    • PDF
    Convolutional Neural Networks for Sentence Classification
    • 6,718
    • PDF
    Collaborative filtering with temporal dynamics
    • 1,413
    • PDF