Predicting attributes for recipients

A system, comprising:

• a memory including computer-executable instructions;
• and
• one or more processors configured to execute the computer-executable instructions and cause the system to:
• receive electronic transaction data indicative of one or more transactions, wherein the one or more transactions are associated with one or more unique providers, and wherein each transaction of the one or more transactions indicates a recipient and one unique provider;
• identify, from the one or more transactions, a subset of transactions that are associated with known values for an attribute with respect to one or more unique recipients, and wherein each transaction of the subset of transactions indicates one unique provider and one unique recipient;
• compute, for each unique provider of the one or more unique providers, a provider feature based on the known values for the attribute with respect to a subset of the one or more unique recipients associated with the unique provider in the subset of transactions;
• compute, for a given recipient indicated in one or more given transactions of the one or more transactions that are not included in the subset of transactions, a recipient feature based on the provider feature of each unique provider of the one or more unique providers that is indicated in the one or more given transactions, the computing the recipient feature comprising:
• combining the provider features of each unique provider of the one or more unique providers that is indicated in the one or more given transactions to generate a combined provider feature, and
• normalizing the combined provider feature based on a sum of components of the combined provider feature;
• and
• predict, by the one or more processors, based on the recipient feature and via a machine learning model, a value for the attribute with respect to the given recipient.

A non-transitory computer readable medium comprising instructions to be executed in a computer system, wherein the instructions when executed in the computer system cause the computer system to:

• receive electronic transaction data indicative of one or more transactions, wherein the one or more transactions are associated with one or more unique providers, and wherein each transaction of the one or more transactions indicates a recipient and one unique provider;
• identify, from the one or more transactions, a subset of transactions that are associated with known values for an attribute with respect to one or more unique recipients, and wherein each transaction of the subset of transactions indicates one unique provider and one unique recipient;
• compute, for each unique provider of the one or more unique providers, a provider feature based on the known values for the attribute with respect to a subset of the one or more unique recipients associated with the unique provider in the subset of transactions;
• compute, for a given recipient indicated in one or more given transactions of the one or more transactions that are not included in the subset of transactions, a recipient feature based on the provider feature of each unique provider of the one or more unique providers that is indicated in the one or more given transactions, the computing the recipient feature comprising:
• combining the provider features of each unique provider of the one or more unique providers that is indicated in the one or more given transactions to generate a combined provider feature, and
• normalizing the combined provider feature based on a sum of components of the combined provider feature;
• and
• predict, based on the recipient feature and via a machine learning model, a value for the attribute with respect to the given recipient.