Valve is today rolling out a machine-learning-powered “Interactive Recommender” trained on “billions of play sessions” from the Steam user base. Valve is hoping to improve on its recommendation system by using AI.
According to Valve:
“This experiment looks at how much you’ve played each game in your Steam library, and uses the magic of machine learning to recommend games you might like. Filter your results by picking games that are popular or niche, and drill down by release date and tags.”
“The idea is that if players with broadly similar play habits to you also tend to play another game you haven’t tried yet, then that game is likely to be a good recommendation for you.”
“The best way for a developer to optimize for this model is to make a game that people enjoy playing.”
“We’ve found that, especially for people who play a lot of games, digging into the ‘niche’ end of the range can be a very effective way to find hidden gems.”
Steam has launched something called Steam Labs where it can try strange, experimental things like the sales gimmicks in a special space.
The two other projects are meant more to sell you on games than to suggest them. Micro Trailers shows you six-second clips on a page to give you a feel for many games in a short space of time. And if you have the time The Automated Show provides a half hour video of recent Steam debuts to help you find a potential gem. You probably won’t use these as much as the Recommender, but it won’t hurt to give them a shot. And remember, Valve is using Labs as a sounding board. Whatever proves popular could shape future experiments, not to mention Steam as a whole.