The Universal Recommender v0.4.0

Changes in v0.4.0

• This version requires PredictionIO-0.9.7-aml found here.
• New tuning params are now available for each "indicator" type, making indicators with a small number of possible values much more useful—things like gender or category-preference. See docs for configuring the UR and look for the indicators parameter.
• New forms of recommendations backfill allow all items to be recommended even if they have no user events yet. Backfill types include random and user defined. See docs for configuring the UR and look for the rankings parameter.

Universal Recommender v0.3.0

If you are using the standard single tenant version of PredictionIO you must use the ActionML fork here. Look for v0.9.6 or higher. You will only need the Universal Recommender source since it is built with pio build.

The jars are for use with the ActionML's multi-tenant version of PredictionIO. Put the jars in $PIO_HOME/plugins before the first pio deploy.