WHAT PERCENT OF STEAM GAMES ARE NEVER PLAYED HOW TO
Valve's page explaining the Discovery Queue provides a good overview on how to use the system, and I recommend you give the page a read if you aren't familiar with the system. Determining what things might fit a user's particular tastes is challenging but potentially very helpful. One final tool that I think is key to a good recommendation system is personal relevance. And critically, low popularity does not imply low quality. While popularity tends to be correlated with quality, something doesn't have to be good to be popular. Review scores can gloss over a lot of subtlety, but they give a number that is easy to incorporate into an algorithm. Critic and user scores attempt to put a numeric value on quality. This can be difficult to pin down, since quality can be extremely subjective. But when a lot of people like something, it is a strong signal that it might be interesting.Īnother factor in creating good recommendations is quality. And popularity-based recommendations means that hidden gems will inevitably be missed. Basing discovery recommendations on popularity has its downsides, as people are likely already aware of popular things. One of the most common and straightforward tools to apply is popularity. There are a lot of considerations to make in the design of a recommendation system. The Discovery Queue does not repeat itself, so each of the games I saw was being recommended for the first time. One page states that "It does not change what kind of games will be recommended to you." A different page claims "We will also exclude these products from being used to recommend you other, similar items." During the experiment, I did not mark any additional products as Not Interested. I had seen 1323 products, and I marked 339 of them as "Not Interested." The impact of marking a product as Not Interested is unclear. Prior to starting this experiment, I was a semi-regular user of the Discovery Queue feature. In my Discovery Queue preferences, Early Access Products, Software, Videos, and Unreleased Products are all allowed. I haven't set any tags in Steam's Tags to Exclude feature. My Steam account preferences are set to allow mature content to be shown, with the exception of Adult Only Sexual Content. Valve could have been making subtle tweaks to their algorithms through the whole time, and we would not know it. But I have no way to know if the algorithm has been consistent during the time I was collecting data. I also believe that Valve made further tweaks to the algorithm in early March, which is why I am restricting my sample to the end of February. It offers no insight into how the current algorithm compares to how things worked before October. It's a reasonable assumption that what I'm seeing will generalize to other accounts, but I have no way to know for certain.Īlso, my data only goes back to December 2nd. For one, this only reflects my personal Steam account. There are many caveats regarding the relevance of this data. This is an in-depth breakdown of the statistics and an analysis of the results. I then spent far too many hours obsessing over the data. For each game I was shown, I saved the store page HTML. Between December 2nd and February 28th I viewed 672 games. But I wanted to get a better understanding of how the Discovery Queue works and what games it is showing. Valve hasn't explained what changed back in October.