Machine learning based matching of entities using multiple queues

A non-transitory computer readable storage medium storing instructions that when executed by one or more computer processors cause the one or more computer processors to:

• receive information identifying a plurality of source entities and a plurality of target entities, wherein an entity is associated with one or more resources;
• maintain a plurality of queues, each queue associated with a source entity, wherein each queue comprises one or more target entities, wherein a target entity that matches a source entity is included in a queue of the source entity, the instructions causing the one or more computer processors to:
• extract a feature vector describing the source entity and the target entity,
• provide the feature vector as input to a machine learning model trained to determine a score between an input source entity and target entity, and
• execute the machine learning model to determine the score indicating a matching between the source entity and the target entity;
• one or more times, modify one or more queues from the plurality of queues to optimize an aggregate score across the plurality of source entities and the plurality of target entities;
• for a particular source entity, select a particular target entity from the queue corresponding to the source entity;
• and
• schedule an interaction between the particular source entity and the particular target entity.

A computer system comprising:

• one or more computer processors;
• and
• a non-transitory computer readable storage medium storing instructions that when executed by one or more computer processors cause the one or more computer processors to:
• receive information identifying a plurality of source entities and a plurality of target entities, wherein an entity is associated with one or more resources;
• maintain a plurality of queues, each queue associated with a source entity, wherein each queue comprises one or more target entities, wherein a target entity that matches a source entity is included in a queue of the source entity, the instructions causing the one or more computer processors to:
• extract a feature vector describing the source entity and the target entity,
• provide the feature vector as input to a machine learning model trained to determine a score between an input source entity and target entity, and
• execute the machine learning model to determine the score indicating a matching between the source entity and the target entity;
• one or more times, modify one or more queues from the plurality of queues to optimize an aggregate score across the plurality of source entities and the plurality of target entities;
• for a particular source entity, select a particular target entity from the queue corresponding to the source entity;
• and
• schedule an interaction between the particular source entity and the particular target entity.