TrendMD's article recommendation algorithm

Traditional recommender systems stop at semantic enrichment (i.e. relatedness).

TrendMD’s predictive recommendation engine analyzes hundreds of real-time signals to match people with the top handful of items they are most likely to be interested in consuming next. Our proprietary algorithm sifts through an array of situational factors every time the user loads a web page: collaborative filtering (relatedness, audience click behaviour (“people that read X, also clicked on Y”) and personalization (i.e. what you have read in the past), article popularity, geography, context, referral source, social media trends and more. Operationally, the algorithm takes into consideration behavioral, contextual, and social inputs, as well as general network trends and competition.

Recommendation links dynamically pair with different articles and change locations across our network, based on where they are most likely to receive the highest click-through rate.
Our algorithms are optimized to connect the right content to the right reader, at the right time.



Bottom line: content that is generating the most user interest is given the most volume by TrendMD’s algorithm. It also pulls back on content that is generating less interest. Together, this ensures your budget is being allocated effectively.