Earlier this month, the popular third-party tool Steam Spy was essentially left dead in the water after Valve announced new privacy preferences for Steam users, including hiding libraries and profile data from the public view. This meant Steam Spy, which tracked statistics such as sales and game time of the games, could not access the required data and went offline. But now its creator has returned it, albeit with less reliable data.
Steam Spy creator Sergey Galyonkin has revealed that the site will now use a machine learning model to measure sales figures based on "random data". In his blog post, he announced that his algorithm had predicted 252,000 sales of the new game Frostpunk where the developers betrayed that it had sold 250,000 copies.
Some original features of Steam Spy are not yet available, but you can find the most important statistics such as sales figures and playing time on the website. However, Galyonkin admits that this new version of Steam Spy is far less accurate than before. After testing the algorithm in 70 games, he found 90% of the predictions within a 1
In the meantime, he will continue to work on improving the tool's predictions and bringing back some of the missing features. "I believe in giving everyone access to the essential information, but until I fix everything, Steam Spy will be half-closed to the general public."
SOURCE Steam Spy blog