Content Affinity Engine Introduction

The Lytics Content Affinity Engine is a programmatic approach to content classification and topic affinities at the user level.

There are three main benefits of the Lytics Content Affinity Engine, when comparing it to other solutions:

  1. Automatic rich topic extraction per URL or document
  2. Individual topic affinities for every user
  3. A dynamic taxonomy

Automatic Rich Topic Extraction

Since Lytics collects and stores every event without any aggregation, automatic topic extraction becomes a possibility. For every URL seen, Lytics fetches the web page at that URL, analyzes the content, the metadata, and even the images1. The analysis boils the web page down to a set of topics. Where manual topic tagging may result in four or five topics for an article or product, Lytics topic extraction often results in 10 or more.

Read more about topic extraction

Individual topic affinities for every user

Through automatic rich topic extraction, each URL has a set of topics. Through Data Collection and User Fields, each user has a set of URLs visited. Given the link between URLs visited and topics for URLs, Lytics can algorithmically calculate which topics a user has shown interest in.

Read more about topic affinities

Dynamic Taxonomy

By using a set of data science techniques to look at topic overlap between classified content, Lytics will programmatically build a topic taxonomy. In addition to bulding this taxonomy, Lytics dynamically adjusts the taxonomy as new content gets published.

The topic taxonomy is stored as a weighted and directional graph. Although this structure may be daunting to look at — and even more daunting to try and utilize by hand — Lytics makes use of it when determining content recommendations.

Read more about topic taxonomy


  1. Image analysis is not enabled by default. Contact customer success to discuss options.