The algorithm used by this engine counts unique user-item interactions, giving more relevance to those items and users with a higher number of positive interactions. This engine is particularly effective to produce top-like rankings or recommendations (i.e. most read news).
The first step to make recommendations is to load items, users and interactions data into the system. It can be imported individually or in batch. Please note that only the interactions with positive polarity will be taken into account.
Accepted interaction types:
Tags extraction and training
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:
Returns a score, a number between 0 and 100, related to the popularity of the entities in terms of interaction counts.