Recommendation engines, otherwise known as recommender systems, suggest content based on previous behavior or purchases. Such systems typically use one of two approaches: Collaborative filtering creates a predictive model based on a user's previous interactions such as products purchased or viewed. Content-based filtering looks at content or item characteristics and suggests content with similar elements. Amazon, Netflix and music services including Pandora and last.fm use recommendation engines.
David Sogn, RAPP's VP of data science, on Recommendation Engines:
Recommendation engines attempt to discover and apply patterns in data by learning consumers' preferences and adapting brand experiences to their needs or interests. However, a personalization platform can go beyond simply recommending content and advertising. Pioneering data scientists today are powering a new set of consumer use cases that enhance the media viewing experience. For instance, by integrating external data feeds from metadata providers and product review services such as Rotten Tomatoes, the recommender can call related content to appear on a tablet or other device alongside or during a viewing experience.
When performed correctly, such personalization tactics drive higher engagement, increased conversions and greater brand loyalty. Some companies have even gone so far as to realign their business objectives in light of recommender-driven demand, such as Netflix, AT&T, Amazon, Microsoft, Disney and Apple.