The Experiments feature of RevenueProtect allows you to perform A/B testing. A/B testing allows you to determine whether changes you make to a configuration have a measurable impact, or if differences are due to chance (natural variation). This can be used to decide whether or not changes should be deployed to all transactions.
It is important to track the impact of any change you make to your risk configuration, and how this affects false negatives, for example fraudulent transactions missed by the risk management system that usually result in a chargeback. You can also review the impact of false positives (good orders falsely classified as fraud, resulting in missed legitimate revenue).
To use the Experiments feature: