Imagine that you just finished reading an article on a pasta recipe. How would you feel if you were given recommendations on what to read next and each of them featured another pasta recipe? In some cases (e.g, if you were not satisfied with the first recipe), this might do the trick; but, more often than not, you’d probably like to move on to another topic that really interests you.

Outbrain’s founder and CEO has pointed out that the world is brainwashed by relevancy. Digital content recommendations have often been presented as “related links” and have provided just that by relying primarily upon contextual relevancy. At Outbrain, we strive to find the most interesting content for each and every person through personalized recommendations that are interesting to that person but not necessarily related to what they were just reading.

Recently, we dug into our data to see how this notion of “Most Relevant ≠ Most Interesting”  plays out in numbers:

Contextual Relevancy BP Chart 2

We grouped the content in our index into 11 categories (automotive, business & finance, electronics, entertainment, health, home & lifestyle, news, recreation, sports, technology & internet, and travel) and compared the average click-through rate on related content recommendations (from the same category as the current article) vs. unrelated content recommendations (from a different category from the current article).

We found that unrelated content recommendations generated a 16% higher CTR on average!

With more and more data like this, perhaps the “relevancy brainwash” will start to wear off and it will become clearer that the best way to deeply engage audiences is to tailor recommendations to each individual person.