“Valve is launching a new “Interactive Recommender” that generates personalized lists of Steam games users might like based on what they’ve played before. It’s not replacing the platform’s existing recommendation systems, but it’s supposed to give users another way to navigate Steam’s massive backlog of games — especially smaller titles that often get lost in the mix.”
This recommendation system uses machine learning, basically an AI, it checks on what games you play and what other people play, then it makes suggestions on the decision of people playing other games, the idea is that if players will similiar play habits to you plays another game that you haven’t tried, it would be a good recommendation for you.
You can explore the recommendations with tags and sliders, so you can browse only for categories like “Massively Multiplayer” or “Indie”, you can include juste newer release (the slider moves from 10 years to six month) or you can search from “popular” to “niche”.
You can’t remove games from the recommendation list even if you added them in your wishlist or “ignored” them on the store page.
Valve notes that this doesn’t help you to find new games, but mostly to find “hidden gems.”