1. Knowledge Base
  2. Retain
  3. Real-Time Churn Prediction (Sports)

Real-time Churn Prediction for Sports

Amplifier AI’s Real-time Churn Prevention feature boosts revenue by enabling operators to engage players at the optimal moment, with the precision and speed needed to retain those at risk of leaving.

How It Works

Amplifier AI’s churn models analyse bet settlement data in real time, immediately assessing a player’s experience through key behavioural attributes. This rapid evaluation enables operators to engage players proactively, optimising retention at every step.

Typical Player’s Experience Attributes

  • lossPct: Amount lost as a percentage of the highest among the 5 previous losses.
  • Bets24h: Number of bets placed in the last 24 hours.
  • BetsPerDay: Average number of bets per day.
  • ActiveDays: Activity in the last 7 days.
  • ActiveDaysPerWeek: Average activity per week.
  • Stakes24h: Total stake amount in the last 24 hours.
  • StakePerDay: The average stake per day.
  • StakeAmount: The stake amount of the triggering ticket.
  • BetType: The type of the triggering ticket/bet.
  • TotalOdds: The total odds of the current triggering ticket.
  • LossAmount: The loss amount of the existing triggering ticket.
  • BetsLost: Number of consecutive lost bets.
  • BetsLostLossAmount: The cumulative loss amount from a series of consecutive lost bets.

Reason codes

When a player is flagged as at risk of churning, a reason code is assigned, and an API payload is sent back to the operator. This empowers the operator to act swiftly with targeted interventions tailored to the player’s specific churn risk, optimising retention strategies in real time.

  • Bad Beat: lost single bet with odds lower than 1.25 or lost accumulator that has more than 3 selections with only one losing selection.

  • Significant Loss: The amount lost by the user in his last bet is 50% or higher compared to the maximum of the 5 previous losses.

  • Consecutive Losses: Three or more consecutive losses.

  • Reduction in Activity: When the number of bets in the last 7 days is lower than the number of bets in the 7 days prior to that (day 7 - day 14).

  • Reduction in Frequency: When the number of active days (days bet placed) in the last 7 days is less than the number of active days in the 7 days prior to that (day 7 - day 14).

  • Reduction in Spend: The total stakes in the last 24 hours were less than the average daily stake.

  • Other (reason code): Churn was predicted but no clear reason code could be identified for churn.



For more details on integrating Real-time Churn Prevention for Sports, please refer to our Integration Requirements Guide, which explains how churn-related insights are seamlessly relayed back to operators for prompt intervention.

Still have questions? Check out our FAQs for further assistance.