Learn about FERN-based matching

Flexible Entity Resolution Network (FERN)-based models for individual type entities such as a contact or a broker agent enable pretrained models that automate real-time matching. Based on your pretrained models, the individual type entities match with the internal or external source as configured. You can define the matches based on the attributes including names, phone numbers, email addresses, and so on.

For example, you have 20,000 potential matches currently in your queue. You have to go through every single one of them to resolve and spend time on every single pair to decide whether it's a match or not a match. If you enable FERN, it provides a score for every single potential match. Based on your settings, with FERN enabled, you may have 7,000 of them getting a very high score that you can focus on. This way, FERN enables you to improve your productivity with high accurate rate of matches.

For more information, see topic Enable a pretrained FERN model.