1. Knowledge Base
  2. Retain
  3. Bonus Recommendations (Sports)

Data Onboarding

This section summarises how operator systems’ can integrate with Amplifier AI’s Bonus Recommendation Engine for seamless onboarding

The data onboarding involves the following steps (the first two can be seen below):

  • Data Investigation 
  • Real-time (or) Batch integration 
  • Data transformation 
  • Model testing in staging environment 
  • Launch 

1. Data Investigation 


In the onboarding process, Anthem requests a sample data from operators to assess whether the necessary fields required for modelling and analytics are present in the data sample. 

The key data elements we typically require include: 

User and ticket details 

  • Client ID 
  • Bonus ID 
  • Transaction ID 

Bet Information: 

  • Bet amount 
  • Event or Sport Name 
  • Bet time 
  • Bet status 
  • Bet settlement status 
  • Balance 

Bonus data 

  • Description 
  • Bonus amount 
  • Bonus time 
  • Bonus type 

 

Data Requirements 

In any onboarding process, the volume and nature of the data, as well as the integration of that data are crucial for a seamless onboarding experience. 

  1. Data volume: Anthem typically requests a minimum of one year of historical data, and data spanning up to 4 years is recommended considering events such as the World cup that occur over a 4 year cycle. Having more data leads to improved engine recommendations. 
  2. Data type: The type data required for bonus calculation will be determined by how each customer defines Customer Lifetime Value (CLTV). CLTV is typically calculated as the average lifetime of players on the platform multiplied by net game revenue. To accurately calculate the Net Gaming Revenue (NGR), access to transactional data is necessary. This includes information such as user ID, time of bet, amount of bet, amount of return, bonus ID, type of bonus, registration information, and bonus consumption details.

    Here is an example of the type of data that clients have provided: 

    Bet Information: 

    • ticket_time_bet: The time when the bet was placed. 
    • ticket_time_evaluation: The time when the bet was settled. 
    • oppty_end_time: The time after which no more bets can be placed. 
    • ticket_total_bet: The bet amount after tax reduction. 
    • ticket_total_pay: The bet amount before tax reduction. 
    • ticket_win_to_pay: The bet payout amount. 
    • ticket_number: The unique identifier for the ticket coupon. 
    • ticket_possible_win_to_pay: The maximum possible win amount for the ticket. 
    • ticket_total_odds: The total odds associated with the bet, regardless of the bet type. 

    Ticket Evaluation: 

    •  id_ticket_item_evaluation_state: The evaluation state of ticket items, indicating if they are unresolved, winning, non-winning, payback, or rejected. 
    • ticket_item_odds_value_bet: The odds associated with the bet items. 
    • ticket_item_odds_value_pay: (Further clarification may be needed). 

    Ticket State: 

    • id_ticket_state: The numerical ID representing the state of the ticket. 
    • ticket_state_name: The descriptive name of the ticket state (prematch and live), indicating the status of the ticket, such as saved, accepted, canceled, winning, non-winning, cashed, etc. 

    Bonus and Tax Information: 

    • ticket_win_fee_value: Additional tax applied to high winnings (over a certain threshold), typically a percentage of the winnings. 
    • Ticket_client_change_credit: Indicates the type of credit change, such as real cash deposit or bonus money. 
  3. Data Input: Our primary method for data input is through real-time data integration via an API. Alternatively, we also support data input through CSV file uploads to an SFTP server. To initiate the SFTP server connection, please coordinate with our team for access. The frequency of CSV file uploads will be determined based on an agreement between two parties, and the schema required by your systems will be established in collaboration with our team. 

2.  Real-time (or) Batch Integration 

Anthem acquires data either in real-time or batch integration, depending on the operational preferences of the operators. When opting for batch integration, operators are required to send the data files based on the agreed-upon frequency and time period.