The University of Washington graduates 74% of its students: meaning that 26% of students do not complete their studies. Students who churn (or “drop out”) from the University of Washington end up spending a significant amount of time and money and ultimately receive no benefit. State governments and the federal government together spend ~$2.9 billion per year in grants and loans to first year students who will not return to school, representing a significant waste of taxpayer dollars. The first step in improving student retention at the University of Washington is identifying the students who are at the greatest risk to churn from the school. This information can be passed to counselors or department specific administration staff who can then target retention efforts at the students who need it most. The work is twofold: first, machine learning algorithms were trained on University of Washington transcript data from the period of 1970 to 2013. The feature set was loosely classified into four categories: classes taken, class performance, demographic data, and high school performance. These algorithms provided an 87% prediction accuracy of student dropouts. A feature engineering approach is now underway to further improve performance. This involves expanding the feature set by creating composite features and modified features. Composite features will allow the machine learning algorithms to weight relationships between features in addition to the features themselves (e.g. an engineering student with a poor math GPA may be more likely to churn). Modified features include some mathematical function of the original feature (log, square, multiplied, etc.). This allows for different (and potentially much greater) feature weights without suffering the penalties imposed by algorithm regularization. These two approaches to feature engineering will allow for an improvement over the previously observed 87% accuracy.

At full capacity, the University of Washington-Seattle Campus plays host to nearly thirty thousand undergraduates and fourteen thousand graduate and professional students. UW-Seattle provides an enormous amount of information to help students navigate over one hundred and eighty majors and degree programs. Lack of standardization and the diaspora of information across many department websites, however, makes it very difficult for students to effectively discover and plan course work, especially over their entire undergraduate or graduate career at the university. The Coursector Project seeks to address this disparity between the amount of information available for students and unfortunately complex nature of its structure: much of the information about courses and offerings is simply in text, with no visual aids or recommendation engines for students. By building web-ready data visualizations about course prerequisite relationships, the project allows students to see links between courses, majors, and areas of their interest. These interactive visualizations are made up of data scraped from the UW course catalog. Beyond using it for practical course planning purposes, students can also simply mess with the visualizations for fun, discovering new classes and course pathways they had not previously thought of. Furthermore, because of the interwoven nature of many interdisciplinary offerings at the University of Washington, many departments rely on one another for prerequisite courses and instruction. The data analysis and visualizations performed by the Coursector Project will also allow school administrators to address so called choke point classes: those which unlock access to many upper level classes in any given department. The data is all there. The Coursector Project helps students and staff alike make sense of it.