Content based engine

The algorithm used extracts descriptive information from text attributes and builds recommendations based on the similarities to users' preferences, based upon users' past interactions. Therefore, the main data sources of this engine are the string fields of the item catalog, particularly, long texts. Some paradigmatic examples of items and fields that fit into this model are the headers and bodies of news items and the detailed description of a product.

Content-based engine diagram

Using NLP, the engine analyzes those texts to characterize the items. Based on information retrieval techniques, every user gets an individualized profile, which is updated after every interaction. When building a recommendation, the algorithm looks for items similar to those that the user has interacted with in the past, according to their profile.

Usage

Data

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.

Accepted interaction types:

unarybinarycategoricalcontinuous

Tags extraction and training

In order to make recommendations, the engine needs to be trained. When the training runs, tags are extracted from the relevant text attributes and the training is performed based on them. Then the model is ready to make recommendations.

You can find more details about the training in Training.

Recommendations

After the model has been trained, recommendations can be made. This engine can make recommendations for the following user-item combinations:

UsersItems
Users
Items

Diversity

Not available.

Output

The result of the recommendation is a list of users/items to recommend.