Automatic Tokenization of Features Using Machine Learning

A method for enhanced generation of a recommendation for a user account, using multiple machine learning (ML) models, comprising:

• at a computing platform comprising at least one processor, and memory:
• receiving account information associated with the user account, wherein the account information comprises historical account data and one or more user-defined account rules;
• inputting, into a user ML model, the account information;
• processing, by the user ML model, the historical account data and the one or more user-defined account rules to determine a plurality of account features;
• outputting, by the user ML model, the plurality of account features;
• receiving, from a media platform, unstructured media data;
• inputting, into a media ML model, the unstructured media data;
• processing, by the media ML model, the unstructured media data to determine a plurality of media features;
• outputting, by the media ML model, the plurality of media features;
• inputting, into a recommendation ML model, the plurality of account features and the plurality of media features;
• generating, by the recommendation ML model, tokens representing each of the plurality of media features and each of the plurality of account features, wherein the tokens are connected together in a fully connected graph structure;
• deleting, by the recommendation ML model, each of the tokens representing media features not matching with any of the tokens representing the plurality of account features;
• processing, by the recommendation ML model, a recommendation score based on the tokens in the fully connected graph structure representing the plurality of account features and the plurality of media features;
• outputting, by the recommendation ML model, the recommendation score;
• generating the recommendation for the user account based on the recommendation score;
• and
• sending, to a user computing device associated with the user account, the recommendation.

One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, and memory, cause the computing platform to:

• receive account information associated with a user account, wherein the account information comprises historical account data and one or more user-defined account rules;
• input, into a user ML model, the account information;
• process, by the user ML model, the historical account data and the one or more user-defined account rules to determine a plurality of account features;
• output, by the user ML model, the plurality of account features;
• receive, from a media platform, unstructured media data;
• input, into a media ML model, the unstructured media data;
• process, by the media ML model, the unstructured media data to determine a plurality of media features;
• output, by the media ML model, the plurality of media features;
• input, into a recommendation ML model, the plurality of account features and the plurality of media features;
• generate, by the recommendation ML model, tokens representing each of the plurality of media features and each of the plurality of account features, wherein the tokens are connected together in a fully connected graph structure;
• delete, by the recommendation ML model, each of the tokens representing media features not matching with any of the tokens representing the plurality of account features;
• process, by the recommendation ML model, a recommendation score based on the tokens in the fully connected graph structure representing the plurality of account features and the plurality of media features;
• output, by the recommendation ML model, the recommendation score;
• generate the recommendation for the user account based on the recommendation score;
• and
• send, to a user computing device associated with the user account, the recommendation.