When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

Steam's recommended games should now be more accurate following Valve experiments

The game recommendations the Steam store feeds to its customers through the "Recommendation Feed", "More Like This", and "Recommended for You" sections of the store have been given some under-the-hood polishing by Valve, making the systems present users with more personalized and varied selections of games.

To accomplish this, Valve has been experimenting with changing the recommendation algorithm and fixing bugs that were plaguing the aforementioned sections. Before these changes, the store had been showcasing games primarily from the top-rated and popular games lists.

To test the new code and bug fixes, Valve had shipped the changes to 5% of Steam customers in the past few weeks. It had found that customers in this experiment pool would now click on games in the recommended section almost 15% more than the untouched group. The company also saw a 75% increase in the unique games discovered by these users and a 48% jump in average visits per game.

"Store areas driven by Tags, such as 'More Like This,' saw increases in purchase and wishlisting across a broader set of games," added Valve in its blog. "It shouldn't come as much of a surprise, but by increasing qualitative specificity and showing a wider range of titles, more customers found things they didn't know they wanted."

Satisfied by the successful experiment, Valve has now rolled out the algorithm changes and bug fixes to the entire Steam userbase, meaning everyone should now start seeing more games that fit their tastes being recommended to them. Meanwhile, Valve is also prepping to finally launch the Steam Library overhaul update soon, which is slated to land in beta form on September 17.

Report a problem with article
Next Article

Microsoft details 2019 release wave 2 features for Power BI in an overview video

Previous Article

Screenshots leak of new Windows 10 Calendar app

Join the conversation!

Login or Sign Up to read and post a comment.

0 Comments - Add comment