A new Steam Labs experiment will tell users what game they should play next.

As announced in a blog update, the new experiment - titled Play Next - will use the same technology as the Interactive Recommender.

The feature is a work-in-progress meaning it could face substantial changes before it officially launches to users, assuming it rolls out at all. 

"Our machine learning system helps you to choose, by suggesting the games it thinks you'll enjoy most, among games you already own," said the update.

"Up to three selections are shown at a time. If the first set doesn't quite grab your attention, you can cycle through to see other suggestions when available.

"To help you see at a glance what kind of game each of our suggestions is, we include a micro trailer (on hover), and the top tags for the game. If you've already played some comparable games, we show some of those too."

The update concluded: "The algorithm we use for picking comparable games is also a new system we're experimenting within this lab, and it's a work-in-progress. So don't be surprised if it sometimes shows you some unexpected comparison points."

Since the Steam library was updated - in October 2019 - there has been a 300 per cent increase in user reviews. As of November 2019, 2,903 games were removed from Steam's archives.

The interactive Recommender was added to Steam Labs on July 11th 2019, by August 2019, 10,000 games had been added to user wishlists.