CPC G06N 5/022 (2013.01) [G06N 20/00 (2019.01); G06F 40/174 (2020.01)] | 20 Claims |
1. A method of entity predictive matching, comprising:
receiving a description of a transaction associated with an organization;
invoking at least one machine learning model to infer:
a transaction embedding based on the description;
a first score that captures similarity between the transaction embedding and entity embeddings associated with a global list of entities and organizations, wherein the global list is generated by deduplicating an initial set of entities based on a density of a group of entities that satisfies a density threshold;
a second score that captures a probability of interaction between the organization and the global list of entities based on an organization embedding and entity embeddings that capture profile data associated with the organization and the entities; and
at least one candidate entity based on the first score and the second score; and
returning the at least one candidate entity.
|