Systems and methods for instrumentation of education processes

A method comprising:

• obtaining, by one or more computing devices via one or more application programming interfaces (APIs), training data and test data related to student performance for a first plurality of students from one or more student information systems (SISs), the training data and the test data associated with a plurality of variables having influence on performance of an education process;
• select one or more subsets of data from the training data to reduce a number of the plurality of variables to use for generating a machine learning model, the one or more subsets of data representing one or more indices based at least on one or more individual questions and describing a theme;
• generating, by one or more computing devices, using one or more subsets of data, the machine learning model to simulate the performance of the education process, the machine learning model to predict a performance outcome of a student based at least on information received by the plurality of students identified by the one or more subsets of data (i) representing a network of nodes corresponding to a respective subset of variables of the plurality of variables, and (ii) illustrating for each variable of the plurality of variables a respective predicting strength of predicting the performance of the education process;
• validating, by one or more computing devices, the machine learning model using the test data;
• and
• providing, by one or more computing devices, a visual representation of the machine learning model for display one or more client devices.

A non-transitory computer-readable product including computer code instructions stored thereon, the computer-code instructions, when executed by one or more processors, cause the one or more processors to:

• obtain via one or more application programming interfaces (APIs) training data and test data related to student performance for a first plurality of students from one or more student information systems (SISs), the training data and the test data associated with a plurality of variables having influence on performance of an education process;
• select one or more subsets of data from the training data to reduce a number of the plurality of variables to use for generating a machine learning model, the one or more subsets of data representing one or more indices based at least on one or more individual questions and describing a theme;
• generate, using one or more subsets of data, the machine learning model to simulate the performance of the education process to predict a performance outcome of a student based at least on information received by the plurality of students identified by the one or more subsets of data, the model (i) representing a network of nodes corresponding to a respective subset of variables of the plurality of variables, and (ii) illustrating for each variable of the plurality of variables a respective predicting strength of predicting the performance of the education process;
• validate the machine learning model using the test data;
• and
• provide, for one or more client devices, access to the machine learning model.