Every year, academic institutions invest considerable effort and substantial resources to influence, predict and understand the decision-making choices of applicants who have been offered admission. In this study, we applied several supervised machine learning techniques to four years of data on 11,001 students, each with 35 associated features, admitted to a small liberal arts college in California to predict student college commitment decisions. By treating the question of whether a student offered admission will accept it as a binary classification problem, we implemented a number of different classifiers and then evaluated the performance of these algorithms using the metrics of accuracy, precision, recall, F-measure and area under the receiver operator curve. The results from this study indicate that the logistic regression classifier performed best in modeling the student college commitment decision problem, i.e., predicting whether a student will accept an admission offer, with an AUC score of 79.6%. The significance of this research is that it demonstrates that many institutions could use machine learning algorithms to improve the accuracy of their estimates of entering class sizes, thus allowing more optimal allocation of resources and better control over net tuition revenue.

Introduction Many individual faculty have surveyed their students about classroom voting, and they generally report positive results. How robust are these results across a wide variety of students, campuses, instructors, and courses? In this study, a total of 513 students in 26 classes were surveyed regarding the use of classroom voting in their classes. (See Appendix A for the survey form.) Fourteen instructors from ten different schools participated. The classes surveyed were primarily freshman and sophomore level courses in calculus, multivariable calculus, linear algebra, and differential equations. While several questions show the variation in response that one might expect, other questions generate consistent results, showing that student opinion in these areas is uniform across many variables. Aggregate Results The aggregate results are overwhelmingly positive. 93% of the students surveyed say that voting makes the class more fun. While having fun certainly does not equate to learning, it is a good first step and tends to encourage attendance. 90% of the students say that voting helps them engage in the material, and 84% say it helps them learn. Students love examples and always seem to be clamoring for more. About half of the students surveyed (48%) say that they would be better prepared for the homework and exams if the instructor did more examples on the board and less voting. Given that students are so enamored of examples, this response is not unexpected.