Using predictive modeling methods, it is possible to identify at-risk students early and inform both the instructors and the students. While some universities have started to use standards-based grading, which has educational advantages over common score-based grading, at–risk prediction models have not been adapted to reap the benefits of standards-based grading in courses that utilize this grading. In this paper, we compare predictive methods to identify at-risk students in a course that used standards-based grading. Only in-semester performance data that were available to the course instructors were used in the prediction methods. When identifying at-risk students, it is important to minimize false negative (i.e., type II) error while not increasing false positive (i.e., type I) error significantly. To increase the generalizability of the models and accuracy of the predictions, we used a feature selection method to reduce the number of variables used in each model. The Naive Bayes Classifier model and an Ensemble model using a sequence of models (i.e., Support Vector Machine, K-Nearest Neighbors, and Naive Bayes Classifier) had the best results among the seven tested modeling methods
Integrating more engineering contexts, introducing advanced engineering topics, addressing multiple ABET Criteria, and serving under-represented student populations in foundation engineering courses are some of the opportunities realized by the use of a new framework for developing real-world client-driven problems. These problems are called Model-Eliciting Activities (MEAs), and they are based on the models and modeling perspective developed in mathematics education. Through a NSF-HRD Gender Equity Project that has funded the development, use, and study of MEAs in undergraduate engineering courses for increasing women's interest in engineering, we have found that the MEA framework fosters significant change in the way engineering faculty think about their teaching and their students. In this paper, we will present the six principles that guide the development of an MEA, detail our motivation for using the MEA framework to construct open-ended problems, and discuss the opportunities and challenges to creating, implementing, and assessing MEAs.