Alloy now allows you to make workflow decisions based on a proprietary dataset or model. For example, your company may have its own fraud model based on your own device and location data that you would like to apply in a workflow. Custom models were previously supported but now clients can set up these models much more quickly and independently.

We now allow clients to configure a “Custom Model” service within an Alloy workflow in the following way:

1. You host and configure an endpoint that Alloy will POST to during an evaluation with any service data that have been configured to run before the custom model
2. Your model returns a score to Alloy
3. You can configure decision thresholds based on that score in the Alloy dashboard

To learn more about how to use custom models, please reference our support documentation.

We have updated the Diligence panel to provide more contextual information on each of the fraud scores, making it easier to quickly assess the risk of each Entity. On the Diligence panel, third party fraud scores are now color-coded to reference each vendor’s best practice ranges. Green indicates low risk, orange is moderate risk and red is high risk.

When a user clicks the score, they will see more information about that specific fraud service and how they generate their score. This contextual information will give users clear insights to determine the next steps for each Entity.

The Manual Review modal for an Entity now displays the name of the Entity for contextual reference.

Quickly assign an existing role permission to a new agent upon creation.

You can always modify role permissions post creation by clicking into a specific agent as previously supported.

The Group Detail view has been updated to be consistent with that of the current Group Review view. The difference between the two views is the ability to take action and review when accessing a group through the Review Queue.

Before Group Detail View

After Group Detail View

Determine when core PII was used in the evaluation but not verified or unverified by a third party service. Previously, we only showed a default string that represented none were matched. Now, you’ll see each section split out within matched data.

Before

After