Machine learning using secured shared data

A system comprising:

• one or more processors of a machine;
• and
• a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising:
• sharing, on a database system, a database application to a first user of the database system, the database application generated by a second user of the database system, the database application comprising a machine learning model for training on a training dataset, the training dataset comprising:
• a first database training dataset from the first user of the database system;
• and
• a second database training dataset from the second user of the database system, the first database training dataset and the second database training dataset including non-overlapping dataset features;
• sharing, on the database system, encrypted data from the second user in a secure encrypted view;
• sharing one or more functions of the database application, the one or more functions configured to access the encrypted data in the secure encrypted view;
• identifying a query from the first user, to train the machine learning model on the training dataset;
• generating, on the database system, an encrypted trained machine learning model by training the machine learning model on a joined dataset according to the query, without decrypting the encrypted data from the second user;
• and
• generating, on the database system, one or more outputs from the encrypted trained machine learning model by applying the encrypted trained machine learning model on new data.

A machine storage medium embodying instructions that, when executed by a machine, cause the machine to perform operations comprising:

• sharing, on a database system, a database application to a first user of the database system, the database application generated by a second user of the database system, the database application comprising a machine learning model for training on a training dataset, the training dataset comprising:
• a first database training dataset from the first user of the database system;
• and
• a second database training dataset from the second user of the database system, the first database training dataset and the second database training dataset including non-overlapping dataset features;
• sharing, on the database system, encrypted data from the second user in a secure encrypted view;
• sharing one or more functions of the database application, the one or more functions configured to access the encrypted data in the secure encrypted view;
• identifying a query from the first user, to train the machine learning model on the training dataset;
• generating, on the database system, an encrypted trained machine learning model by training the machine learning model on a joined dataset according to the query, without decrypting the encrypted data from the second user;
• and
• generating, on the database system, one or more outputs from the encrypted trained machine learning model by applying the encrypted trained machine learning model on new data.