Student-created cheat sheets have been used to reduce exam anxiety, de-emphasize memorization, and enable students to focus on high-level learning. Previous work has identified cheat sheet properties which correlate with exam performance and has shown conflicting results about the benefits of cheat sheets for different subjects. However, no such study has been conducted for more advanced courses requiring knowledge from different fields and different representations, such as text, code, formulas, and images.

We investigate which characteristics of student cheat sheets predict exam performance for a third-year Computer Graphics and Image Processing course. Our results show that higher exam scores are correlated with a better coverage of course material and more formulas, but not with having more images/diagrams, which were surprisingly few. Having many example questions with sample solutions and missing lecture topics was correlated with lower grades. We hope to use our results to help students to better prepare for exams and create more effective cheat sheets.