Mahout
  1. Mahout
  2. MAHOUT-1089

SGD matrix factorization for rating prediction with user and item biases

    Details

    • Type: New Feature New Feature
    • Status: Closed
    • Priority: Major Major
    • Resolution: Fixed
    • Affects Version/s: 0.7
    • Fix Version/s: 0.8
    • Labels:
      None

      Description

      A matrix factorization that is trained with standard SGD on all features at the same time, in contrast to ExpectationMaximizationFactorizer, which learns feature by feature.

      Additionally to the free features it models a rating bias for each user and item.

      1. RatingSGDFactorizer.java
        7 kB
        Zeno Gantner
      2. MAHOUT-1089.patch
        9 kB
        Sebastian Schelter
      3. RatingSGDFactorizer.java
        8 kB
        Zeno Gantner

        Activity

        Suneel Marthi made changes -
        Status Resolved [ 5 ] Closed [ 6 ]
        Suneel Marthi made changes -
        Fix Version/s 0.8 [ 12320153 ]
        Affects Version/s 0.7 [ 12319261 ]
        Sebastian Schelter made changes -
        Status Patch Available [ 10002 ] Resolved [ 5 ]
        Resolution Fixed [ 1 ]
        Zeno Gantner made changes -
        Attachment RatingSGDFactorizer.java [ 12551238 ]
        Sebastian Schelter made changes -
        Attachment MAHOUT-1089.patch [ 12547198 ]
        Zeno Gantner made changes -
        Attachment RatingSGDFactorizer.java [ 12547180 ]
        Zeno Gantner made changes -
        Comment [ completely new file ]
        Zeno Gantner made changes -
        Status Open [ 1 ] Patch Available [ 10002 ]
        Sebastian Schelter made changes -
        Field Original Value New Value
        Assignee Sean Owen [ srowen ] Sebastian Schelter [ ssc ]
        Zeno Gantner created issue -

          People

          • Assignee:
            Sebastian Schelter
            Reporter:
            Zeno Gantner
          • Votes:
            0 Vote for this issue
            Watchers:
            5 Start watching this issue

            Dates

            • Created:
              Updated:
              Resolved:

              Development