5POINT Protected
Every Decision Evaluated
Decision Level Machine Learning
By looking at human errors from more than 15M live match decisions, we've trained a model to recognise positions where even elite players tend to make mistakes. Using this model, we can estimate the probability that a human player will make an error in any position.
​
This helps to identify 'humanness' over a large set of decisions. Strong performance in difficult positions becomes suspicious quickly.
Advanced Gameplay Statistical Analysis
Relying on PR to identify integrity issues is useful, but may not be sufficient in all cases. This is why 5POINT offers a more detailed match analysis, by tracking numerous play statistics and player style markers.
​
Comparing a players statistics against their own history, and against other players of a similar skill level, we illustrate a more textured view of the play style fingerprint.
This ensemble of statistics can be used to identify assistance whether from a bot or from account sharing or third party human assistance.
Player History
Experience and history matters when it comes to trust. This is why every game reviewed by 5POINT contributes to player histories. This builds the reputation of legitimate players and highlights anomalies across games.
​
As time goes on, this history improves the trust and reputation of protected games and the players that participate.
Manual Review
We understand that allegations of rule breaches are a very serious and sensitive matter and so our analysis provides evidence to both incriminate the guilty, and to exonerate the innocent.
​
5POINT filters large data sets for the riskiest positions, where the player's decision is most meaningful. Then collates these positions for the TD and 5POINT team to review in a convenient format.
​
This allows for all play to be reviewed quickly, and for any specific player allegations to be addressed promptly and meaningfully.
