Configuring Advanced Options

  1. Leave Ignore constant fields checked to skip fields that have the same value for each record.
  2. Select a PCA method from the drop-down list. Note that GLRM and Power are currently experimental.
    GLRM

    Fits a generalized low-rank model with L2 loss function and no regularization; solves for the SVD using local matrix algebra. This option is enabled only if you checked Use all factor level on the Basic Options tab.

    GramSVD
    Uses a distributed computation of the Gram matrix, followed by a local SVD using the JAMA package.
    Power
    Computes the SVD using the power iteration method.
    Randomized

    Uses the randomized subspace iteration method.

  3. Leave Maximum iterations unchecked to have an unlimited number of training iterations (default). Check the box and enter a number to limit the amount of training iterations.
  4. Click OK to save the model and configuration or continue to the next tab.