The payment fraud score is the computed result of Ravelin’s machine learning analysis that that takes into account over 1000 different fraud signals.
The payment fraud score is a probability of how likely a customer is to be a fraudster. This means the higher the score, the more likely a person is to be a fraudster.
Viewing Payment Fraud Scores
You can view a customer’s score on the customer lists page or a customer’s profile.
There are 3 places where you can see the fraud score:
- On the customers list page in the SCORE column on the left side of the table
- Within the pop out customer list on the left side
- In the Overview on the client profile page
Using Payment Fraud Scores
With payment fraud scores you can prioritise the recommendation given to a customer based on the machine learning output. You can determine your score thresholds based on your tolerance for risk and bandwidth for manual review.
- Genuine scores: These users are likely good and don’t require review. Ravelin will tell your application to ALLOW the customer to place an order.
- Review scores: These customers need review. It is unclear if they are good or bad, you may need to challenge the order or dive into the customer profile and do a manual review. Ravelin will tell your application to REVIEW the customer’s order.
- Fraudster scores: These customers are likely bad and should be automatically blocked. Ravelin will tell your application to PREVENT the customer from placing an order.
Note: If you would like to update your scores thresholds, please contact email@example.com.
Payment Fraud Score Contributions
We have grouped contributions so it's easy to understand why a customer has a given score.
- Identity - Looks at information about the customer. For example, the name, email or phone number.
- Orders - Looks at information relating to an order. This can include things like type of item ordered and transaction velocity.
- Payment Methods - Looks at the different payment methods the customer has used.
- Locations - Looks at the different locations associated with the customer. For example, billing address, delivery address and the customers location when completing the order.
- Networks - Looks at the customer network for things like the number of linked accounts, devices or emails.
For each group you can see the most important contributions that were used to determine the fraud score.
Good customers with very low scores may have no contributions because they don't exhibit any fraudulent behaviour.