Discovering Things We Truly Love

ost existing recommender systems fail to offer us recsplanations (i.e., human-understandable explanations for why they’ve recommended specific things). This makes it difficult for us to estimate how much satisfaction we might experience from a given option. Research in the field of recommender systems shows that recsplanations increase user satisfa... See more

most existing recommender systems do not have access to any data outside of their own supply-side platform. For example, if Lee watches lots of true-crime documentaries on Netflix, then it stands to reason that he might also enjoy listening to true-crime podcasts on Spotify and buying true-crime books on Amazon. But because each of those platforms ... See more

 In practice, most people find that recommender systems do an OK job of finding things that are OK, but that they rarely help us discover things we truly love.

A recommender system is a digital product that uses AI to generate personalized recommendations. Over the past 20 years, recommender systems have come to play a central role on many large online platforms. Some recommender systems run prominently in the foreground of the user experience (UX), and operate as core features or even brands (such as Spo... See more

Today, there are three main approaches to solving discovery problems: Conducting research, asking peers for recommendations and using a recommender system.

Discovery problems are as old as civilization. In recent years, however, the ever-growing role of the internet has suddenly made these problems much more difficult. The reason is simple: In the internet era, we are faced with an overwhelming number of options to choose from. In the mood for some music? Spotify has more than 70 million tracks on off... See more

Before the internet era, most of our discovery problems involved only a handful of options, so simple approaches such as “research all the options” or “ask peers for recommendations” usually provided reasonably good outcomes, reasonably quickly. Fast-forward to today, and our discovery problems typically involve thousands or even millions of option... See more