Newsroom News Breaking Comics Tags RSS
News video games 13 September 2019, 13:35

author: Bart Swiatek

Steam Update Improves Video Game Recommendations

Steam has received an update today that improves the game recommendation system. Changes made by developers should make it easier for players to find titles that are actually of interest to them.

Improvements to the Steam recommendation system.

Today, Valve released a new Steam update. The patch focuses on improvements to the game recommendation system, which should work better with the changes, making it easier for players to find titles they might actually like. The information was provided in a blog note.

"Previously, when customers would look for games by browsing the recommendation feed at the bottom of the homepage or the "More Like This" sections, they weren't seeing as many different games as we would've liked. Furthermore, we were receiving lots of feedback that "Recommended for You," felt too biased towards only the most popular games and didn't feel very personalized. We wanted to determine how to respond to this feedback, so we went in search of bugs and decided to run an experiment," we read.

One of the causes of the problem were common bugs, which concerned tags and the so-called time scale, which is used to calculate the popularity of games.

"We found some bugs, such as the "Similar by Tags" section of the Recommendation Feed, which had a bug that top-rated games (a category that doesn't change very often) were driving too much of what players saw. We changed that. We also found that in some places our timescale used to calculate popularity was too narrow, resulting in unpredictable visibility for some games. So we expanded the time period we use in those calculations, "we read further on.

Valve proves that the modifications to the system have been effective. Developers have measured the number of games whose pages were opened via the "Recommended for you" section. The group of people testing this update reported a large increase in both the number of unique games visited and the average number of page views. This suggests that recommendations are more likely to suggest titles of interest to players.

Effectiveness of the new and old recommendation system.
  1. Steam - official website