System and method for machine learning using multiple models

A system comprising:

• at least one processor;
• and
• a non-transitory computer-readable storage medium having instructions stored which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
• training, using public data as inputs, a public data machine learning model;
• training, using private data as inputs, a private data machine learning model;
• training a public and private data machine learning model, wherein the public and private data machine learning model is trained using a combination of:
• (1) historical public data machine learning predictions output by the public data machine learning model, and (2) historical private data machine learning predictions output by the private data machine learning model;
• executing the public data machine learning model using preprocessed clustered data as input, the preprocessed clustered data obtained by clustering current public data, resulting in a public data machine learning prediction;
• executing the private data machine learning model using current private data as input, resulting in a private data machine learning prediction;
• adding public data machine learning prediction to the historical public data machine learning predictions, resulting in updated historical public data;
• adding the private data machine learning prediction to the historical private data machine learning predictions, resulting in updated historical private data,
• wherein subsequent training of the public and private data machine learning model is based on the updated historical public data and the updated historical private data;
• and
• executing the public and private data machine learning model using the public data machine learning prediction and the private data machine learning prediction as inputs, resulting in a final prediction.

A non-transitory computer-readable storage medium having instructions stored which, when executed by at least one processor, cause the at least one processor to perform operations comprising:

• training, using public data as inputs, a public data machine learning model;
• training, using private data as inputs, a private data machine learning model;
• training a public and private data machine learning model, wherein the public and private data machine learning model is trained using a combination of:
• (1) historical public data machine learning predictions output by the public data machine learning model, and (2) historical private data machine learning predictions output by the private data machine learning model;
• executing the public data machine learning model using preprocessed clustered data as input, the preprocessed clustered data obtained by clustering current public data, resulting in a public data machine learning prediction;
• executing the private data machine learning model using current private data as input, resulting in a private data machine learning prediction;
• adding public data machine learning prediction to the historical public data machine learning predictions, resulting in updated historical public data;
• adding the private data machine learning prediction to the historical private data machine learning predictions, resulting in updated historical private data,
• subsequent training of the public and private data machine learning model is based on the updated historical public data and the updated historical private data;
• and
• executing the public and private data machine learning model using the public data machine learning prediction and the private data machine learning prediction as inputs, resulting in a final prediction.