Uploaded image for project: 'Mahout'
  1. Mahout
  2. MAHOUT-877

Enable the parallel ALS recommender to use implicit feedback data

    Details

    • Type: New Feature
    • Status: Closed
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: 0.6
    • Fix Version/s: 0.6
    • Labels:
      None

      Description

      Mahout's ParallelALSFactorizationJob offers a distributed matrix factorization for computing recommendations. The current implementation is only suited for explicit feedback data (ratings) unfortunately.

      The majority of usecases has to work with implicit feedback however. The paper "Collaborative Filtering for Implicit Feedback Datasets" http://research.yahoo.com/pub/2433 describes a closely related approach that is aimed at implicit feedback data and should easily be integratable into the current ParallelALSJob.

        Attachments

        1. MAHOUT-877.patch
          35 kB
          Sebastian Schelter

          Activity

            People

            • Assignee:
              ssc Sebastian Schelter
              Reporter:
              ssc Sebastian Schelter
            • Votes:
              0 Vote for this issue
              Watchers:
              0 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved: