Understanding How Work Habits influence Student Performance

Understanding the relationship between a student's broader work habits and their performance, particularly on open-ended programming assignments, is key towards being able to guide students towards success. In spite of this, most evidence of student behavior and its relationship to performance is anecdotal. The advent of large-scale courses which use online tools for delivering course content, monitoring the programming environment, and providing automatic feedback as well as grading now makes it possible to dive into the data and develop data-driven methods for understanding how a student's approach to an assignment---from their first exposure to the description of the problem to their final submission of their completed assignment---influences their final performance. This study is a first look at a subset of the data collected from a project-based, online, upper-level course on cloud computing. We examine three raw data streams which include information on the time students spend on reading the project write-up, the timing, grades, and number of submissions they make, and the cloud resources used (both time and cost) in solving the assignment. Using these and several synthetic metrics we were surprised to find that there are few behaviors that are highly correlated to student success. Instead, we find that there is a strong correlation between students who continually apply consistent behaviors over the course of the semester to good final performance in the course. From this we use LASSO to create a predictor (adjusted R2=.48) of final performance based on two kinds of consistency measures across 15 metrics.