Gamasutra: The Art & Business of Making Gamesspacer
View All     RSS
November 18, 2018
arrowPress Releases
  • Editor-In-Chief:
    Kris Graft
  • Editor:
    Alex Wawro
  • Contributors:
    Chris Kerr
    Alissa McAloon
    Emma Kidwell
    Bryant Francis
    Katherine Cross
  • Advertising:
    Libby Kruse






If you enjoy reading this site, you might also want to check out these UBM Tech sites:


Transparency is the key to Steam's discoverability problem, says Valve

Transparency is the key to Steam's discoverability problem, says Valve

May 8, 2017 | By Alissa McAloon

May 8, 2017 | By Alissa McAloon
Comments
    8 comments
More: Console/PC, Business/Marketing



Valve has shared a blog post diving into how upcoming changes aim to improve game discoverability and the company’s reasoning behind both these and other recent changes. 

One of the big shifts coming to Steam in the near future seeks to increase the flow of information between players and the digital storefront, and hopefully garner better feedback on the system in the process. That info will then be used to improve discoverability for developers that release games on Steam.

Previously, Steam would crunch the numbers behind the scenes to decide which games it would recommend to players viewing the store, but wouldn’t explain why it was recommending each game.

“The problem with black box algorithms like this is that it's hard to know when they aren't working as intended,” explains the blog post. “Did we not show a game to a player because the algorithm correctly guessed that the player wouldn't be interested in it? Or because there were other games it thought the player would be more interested in? Or just because of a bug?”

“We had similar problems in the Dota 2 matchmaking system, which was also a black box algorithm. We found that when we better exposed the data around the black box (in that case, the matchmaking ranks of the players), our players understood the black box better, and as a result, were able to better identify cases where it wasn't working correctly.”

Much like in Dota 2, the new system aims to pull back the curtain and tell players exactly why each recommendation was picked. The idea here is that more information means that those same players will be able to communicate the accuracy of those recommendations back to Valve, who can then fine-tune its system to display games that players are more likely to buy. 

And for developers, a more accurate recommendation system means that a game is more likely to appear in front of a player who might be interested in buying and playing that kind of game. This ultimately aims to help alleviate Steam’s discovery problem, though it could take a while for developers to see the effect of this upcoming change.

Two more blog posts about Steam’s philosophy and upcoming changes are due out in the near future. The next one intends to discuss how some users have confused Steam’s algorithms by gaming the system in the past, and how more changes will prevent that in the future.

But game developers should be sure to keep an eye out for the third and final post in the series. That entry will offer more detail on Steam’s replacement for Greenlight, Steam Direct, and talk about the service’s “publishing fee.”



Related Jobs

Monomi Park
Monomi Park — San Mateo, California, United States
[11.16.18]

Senior Game Engineer
Monomi Park
Monomi Park — San Mateo, California, United States
[11.16.18]

Senior Game Designer
Game Circus LLC
Game Circus LLC — Dallas, Texas, United States
[11.16.18]

UI Artist
innogames
innogames — Hamburg, Germany
[11.16.18]

3D Artist - for Elvenar









Loading Comments

loader image