Posted in: Games, Valve Corporation, Video Games | Tagged: Interactive Recommender, Steam, valve

Valve Introduces The Interactive Recommender To Steam

Valve has introduced a brand new item from their Steam Labs wing as you can utilize a new program called the Interactive Recommender. You can turn it on for your account right now at this link, but essentially, this is a way for Steam to recommend new games to you based on a variety of things. From the games you play to the genres you enjoy to developers you prefer, the system takes all of that into account and creates what it believes is a good suggestion of games in their library you might want. You can read a more in-depth description of how it works below, but the key thing to keep in mind is that it's voluntary. In other words, if you're seriously afraid of Steam looking at what you're playing and recommending you stuff, you don't need to use it.

Underlying this new recommender is a neural-network model that is trained to recommend games based on a user's playtime history, along with other salient data. 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. 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. These parameters are exposed to the user, allowing you to select whether to see only recent releases in the results, or go all the way back to include games released a decade ago. Similarly, you can choose whether to see mainstream hits, or deep cuts from the catalog. Regardless of the settings of the sliders, the results will always be personalized and relevant to the individual user.

Unlike more traditional approaches, we don't explicitly feed our model information about the games. Instead, the model learns about the games for itself during the training process. In fact, the only information about a game that gets explicitly fed into the process is the release date, enabling us to do time-windowing for the release-date slider. It turns out that using release date as part of the model training process yields better quality results than simply applying it as filter on the output.

Notably, we do not use information about tags or review scores when creating the model. This means reviews or tags alone simply cannot affect results. The model infers properties of games by learning what users do, not by looking at other extrinsic data. We do allow users to filter the final results by tag, so they can narrow down to the kind of game they're in the mood for at that time, but this isn't part of underlying model.

Enjoyed this? Please share on social media!

Stay up-to-date and support the site by following Bleeding Cool on Google News today!