The statistics behind the game
Player Core Dynamics
Central Player Dynamics works with all of our games and focuses on detecting interruptions in communication between players. Reports related to text and voice communication in games are evaluated using the CPD systems. Game-specific reports like AFK or intentional feeding (inting) have individual game teams in charge.
For text reports, the vast majority of reports running through CPD, there were 120 million games with at least one report resulting in 13 million games where a violation was issued. These violations resulted in actions ranging from warnings to bans of more than 365 days, depending on the nature of the violation and the player’s history of previous violations.
League of Legends and Teamfight Tactics
Our League team is currently issuing around 700,000 penalties a month across text detection, AFK detection, and inting detection.
Leaverbuster, our AFK detection system, monitors every game to make sure players who leave early and affect their teams are punished for it.
We use levels so that players who AFK the most receive more severe penalties. And for ranked games where your teammates are absent, we provide early surrender and LP mitigation so you don’t get punished for your teammates’ lean.
But leaving is only one option to bow mates, the other is to feed. This can be a little harder to track, so we use a learning model that tracks seven different data points across all champions to confidently detect when someone is intentionally feeding and not just misplaying. As we continue to update it, false positives have become extremely rare for the system.
For more information on how the League team is working on player behavior, check out this post from early 2022.
In addition to voice chat, VALORANT’s Social and Player Dynamics team also focuses on AFK and inting. Right now about 27 players out of 1000 who play VALORANT appear AFK. Some of these are bots trying to get XP. But we’ve started to see these bots ending up in lobbies full of other AFK bots, and if no damage is dealt, no experience is gained.
For players who are still at their keyboard but are intentionally launching the game, our input detection currently has one method with another in the works.
The current method takes all inputs and decides whether or not a player’s poor performance was intentional after the game. But this method only catches the bad actors after the fact, it doesn’t help when you’re down 11 rounds and understandably not having a good time.
That’s why the VALORANT team is working on real-time inting detection. But there are a lot of gray areas when it comes to this issue, as poor play can be the result of many potential reasons and intentional casting is a small percentage of them. Once the VALORANT team has gotten the false positives down to a small number, we will implement this new method that will work in conjunction with post-game detection.
Wild Rift processes have evolved in 2022. Previously, AFK detection simply checked if players were making any input. Because some players were getting around this simple detection, we added new layers to make sure a player is actually in the game and making useful inputs, not just moving forward.
2022 also brought a new entry system to Wild Rift that uses machine learning to make sure the reason a player misplays is intentional. Since March 2022, the inting system has detected just under 2,000 instances of intentional game launches. As machine learning, well, learns, this number will likely increase as more incoming players are marked.
And finally, there is wintrading detection. This looks at a variety of factors, including what we call “co-versus” players. These are players who are constantly playing with and against the same group of players. By looking at patterns in co-versus players, the length of games, and the win-loss record for co-contra lobbies, the detection system can identify wintrading.
The importance of transparency
Going from one game to a bunch of titles brought with it a lot of new challenges. With more titles on the horizon, we’re working to instill Player Dynamics thinking early in game design to select better communities from the start.
At the same time, we believe it’s important to be transparent about the data we receive across all of our titles. These are complicated problems and there is no way to really solve them completely. With that said, we are committed to working to improve the gaming experience for all of our players and will be posting more regular updates on the work we are doing to that end.
As always, thank you all for playing.