When to Use Machine Learning: A Course Assignment

Abstract

The number of institutions that offer machine learning courses continues to increase. However, supplementary materials that help instructors teach these courses fail to address an important step in the machine learning process; that is, conceptualizing a problem using a valid input-output relationship. To address this issue, I first review frameworks in extant work before proposing a decision flow. After discussing steps in the decision flow, I present a course assignment that reinforces the concepts in the decision flow. I conclude by discussing the lessons learned after using this assignment in a graduate course at a university in the United States.