PredictionIO is not a recommender. It is a Framework you add templates to. The templates do all the machine learning and can be of many types.
That said if you are using the Universal Recommender here: https://github.com/actionml/universal-recommender <https://github.com/actionml/universal-recommender> the user’s actions in real-time are used to make recommendations—no need to have them in training. However any item to be recommended must be known at `pio train` time. If you have some items that have no events you should provide another method for getting events. Think of Recommenders as part of discovery, which usually includes browsing by category or other property, search, and recommend. Both browse and search will allow users to find items without events and in doing so create events for them. The Universal Recommender adds random recs and the ability to boost items by properties and so can recommend when the are no events associated with items. This should not replace browse or search but can be of some help with new items. Docs here: http://actionml.com/docs/ur <http://actionml.com/docs/ur> On Dec 2, 2016, at 12:34 PM, Harry Li <[email protected]> wrote: Hello, I am sort of confused on how PIO handles the recommendations for products that were not in our training. I understand for handling new users, it recommends the most popular products Harry The information contained in this e-mail message and any attachments is confidential. If the reader of this message is not the intended recipient or an agent responsible for delivering it to the intended recipient, you are hereby notified that any review, dissemination, distribution or copying of this communication is strictly prohibited. If you have received this communication in error, please notify the sender immediately by replying to this e-mail and delete the message and any attachments from your computer.
