Supercell data scientist Jarno Seppänen has explained how Clash Royale uses machine learning to target card sales at individual users.
Speaking at the Games First conference in Finland earlier this year, Seppänen described how Clash Royale uses machine learning to handle aspects of the game’s monetisation. Particularly, how the technology can serve players the most valuable cards for them.
“We’re on a small team, we don’t want to grow the team. Whatever happens on a regular schedule, we try to automate that as much as possible,” said Seppänen. “Then we focus the more human efforts on high-profile events.”
The game determines how many of a particular card the player owns, how close they are to upgrading, and the frequency the player makes purchases - among other factors - to determine what deals to promote on the game’s store.
Many of these factors, like pricing and stack size, are determined by hard-coded design. But machine learning drives the understanding of what cards players are more willing to purchase and what offer to serve the user.
You can watch Seppänen’s full talk in a newly published video below.