Utilizing a protected server environment to protect data used to train a machine learning system

Abstract

Systems and methods for protecting information used to train a machine learning system are described herein. In an embodiment, first data identifying one or more status values of a plurality of personal data records are been sent to a server computer from a processor server and stored in a de-identified manner through a generation of a unique identifier for each personal data record using a unique identifier generation scheme and encrypted using an encryption scheme. Second data comprising a plurality of attributes for each of the plurality of personal data records are also sent to the server computer from a database and stored in a de-identified manner through a generation of the unique identifier for each personal data record using the unique identifier generation scheme and encrypted using the encryption scheme. An external server transmits, to the server computer, instructions to generate a machine learning system and to train the machine learning system using the first data and the second data. The server computer trains the machine learning system only if the first data and second data satisfy a first criterion and transmits the trained machine learning system only if the trained machine learning system satisfies a second criterion. The trained machine learning system is then used by the external server to determine whether to send a media item to one or more computing devices or to determine a value of sending the media item to the one or more computing devices.