Valve "Steam Labs" To Open Experimental Features To Public Testing

Valve

Valve "Steam Labs" To Open Experimental Features To Public Testing

With news that your Steam library will be receiving a total make-over, due to it looking pretty ugly in comparison to other the more snazzy collections offered by competing digital marketplaces, Valve has launched Steam Labs, in an attempt to include the community in the redesign process.

The third and final experiment generates a daily show automatically that highlights newly listed and popular games automatically. It does this by taking into account many factors, such as ratings, and the types of games it thinks you prefer. Now its Steam game store has an experiments hub, too.

Valve explained the functioning of the interactive recommender in a blog post. While Steam does have several ways of finding content, the Interactive Recommender puts a new twist on things.

The Interactive Recommended is created to improve game recommendations on Steam. Now, Valve has made a decision to take this one step further by utilizing machine learning to suggest users games that are more suited to their taste. Interactive Recommender is based on a neural network and employs machine learning to "give players personalized recommendations based on their own individual play patterns".

There's a slider to weigh recommendations by popularity, and another slider that works on age, going from released in the last six months up to ten years.

Micro Trailers, the very first experiment that is available on Steam Labs, allows gamers to "absorb every game in the Steam catalog in just seconds" according to the description. The showcase is divided into categories like top 20 new and popular, top 20 indie, top 10 card games, etc., and appears to grab both new and older titles for display.

The objective of Steam Labs seems to be all about seeing which new features click with the Steam community, and which ones can ultimately get Steam customers buying more games.

The Interactive Recommender allows users to filter through machine learning-recommended games, based on your library and play history.

If Automatic Show proves successful, Valve says it might add multiple types of channels to cover different types of games: indie titles, hidden gems, and more. Valve also promises the Recommender won't force developers to game the system with specific tags, pricing, or advertising styles, although without knowing more about how it works, it's hard to rule out users discovering quirks in the engine. We'll have to wait and see how the current test features fare once they get more eyes on them.

Latest News