Matrix factorization with explicit ratings, learning is performed by stochastic gradient descent.



  • Data

    Data set.

  • Preprocessor

    Preprocessed data.


  • Learner

    The learning algorithm with the supplied parameters

  • Predictor

    Trained recommender. Signal Predictor sends the output signal only if input Data is present.

  • P

    Latent features of the users

  • Q

    Latent features of the items


BRISMF widget uses a biased regularized algorithm to factorize a matrix into two low rank matrices as it’s explained in Y. Koren, R. Bell, C. Volinsky, Matrix Factorization Techniques for Recommender Systems. IEE Computer Society, 2009.


Below is a simple workflow showing how to use both the Predictor and the Learner output. For the Predictor we input the prediction model into Predictions widget and view the results in Data Table. For Learner we can compare different learners in Test&Score widget.