More games are being released on Steam than ever before. Valve’s Steam Labs wants to help you separate the wheat from the chaff.
Steam is PC’s most popular digital gaming storefront, hosting most major releases. Of course, the platform is also home to SteamVR, selling thousands of games for all PC VR headsets. In an age when practically anyone can become a developer and publish something on Steam, it’s becoming increasingly harder to promote worthy titles.
Full Steam Ahead
Steam Labs, then, serves as a hub for experimental tools Valve is testing to remedy those issues. Ideas currently featured include six-second trailers that give you a quick taste of popular games and a weekly automated show lasting around 30 minutes. The show gives you a look at new and popular games, the latest indie titles, top sellers and more.
Perhaps the most significant additions, though, is the Interactive Recommender. This new system uses machine learning to assess data such as your playtime history on certain games and then find suitable recommendations.
Naturally, if you spend a lot of time in VR, you’ll start seeing a lot of VR suggestions. “We train the model based on data from many millions of Steam users and many billions of play sessions, giving us robust results that capture the nuances of different play patterns and covers our catalog,” Valve notes in a blog post. “The model is parameterized so that we can restrict output to games released within a specified time-window, and can be adjusted to prefer games a higher or lower underlying popularity.”
Techniques such as these could play a big role in highlighting better-quality VR games on Steam going forward. We sometimes see as many as 30 new releases for headsets in a week. Many of these are often low-quality shovelware, but it makes picking out the genuinely good content much tougher. With SteamVR recently getting a boost in the form of Valve’s Index headset, better discoverability is sorely needed.