The algorithm used by this engine uses collaborative filtering based on latent factor models. It considers the past behavior of users to profile both users and items, establishing connections between them.
This engine is meant to work on environments where only implicit feedback is available. For instance, websites where the clicks by the users are the only aqcuirable data to analyze are examples of suitable candidates for the ISDV Engine.
Accepted interaction types:
In order to make recommendations, the engine needs to be trained. Then the model is ready to make recommendations.
You can find more details about the training in Training.
After the model has been trained, recommendations can be made. This engine can make recommendations for the following user-item combinations:
Model tags are required to apply diversification. The tags extraction is done by training the model with the Content Based engine.
Every entity included in the list of recommendations comes with a percent match score. This score, a number between 0 and 100, indicates the degree of affinity between the recommended entity and the recipient.