You might have discussed this before I joined the class, but This paragraph from “Playful engineering: Designing and building art discovery systems” that reads “Collaborative filtering also suffers from the “cold start” problem (Schein et al., 2002): a system doesn’t know how to evaluate items that no user has rated yet. It thus requires a strong user base at the outset in order to be effective—no recommender system uses collaborative filtering exclusively—and only gets better with more and more users. While this approach works for Netflix or Amazon, we opted against implementing collaborative filtering at an early stage for the reasons outlined above”.

Reminded me about the “Never Been Seen” project by the Science Museum Group that has digitised hundreds of thousands of objects from its remarkable collection as they are moved to a new, purpose-built store in Wiltshire. Each of these objects were added to the collection website, and you could be the first person to see it published online though a web page which displays objects with a total lifetime page view count of zero. (https://thesciencemuseum.github.io/never-been-seen/index.html?fbclid=IwAR3ZXCcQM-X5nwf8nW0FVgGRyDnKzSWegr593rJpP6fer-Z1Kb86n8vno38)