I'm trying to predict grades within a course at my university. At the moment I manually extracting features, but I'm curious if it's possible to somehow use my entire dataset with a deep learning approach?
I have data from throughout the course of students solving mandatory exercises. All students uses a plug-in within the editor that takes a snapshot of code-base each time the student saves the project (exercise). I also have data from when the students run the debugger. All exercises include tests which determine what score the student will receive on a given exercise. The students are free to execute the tests as many times as they like wile solving the exercise (the final score is given when the students presents the final result to a teaching assistant). Execution and results of these tests are also included in the data. Timestamps exists for all data. I also have the final grade of each student (which is determined 100% by the final exam).
Does anyone know of an approach to use this kind of data with a deep learning approach?
