White House, Department of Education, and Chronicle of Higher Education highlight our college recommendation software
Two organizations have joined forces to answer important questions related to how search, discovery and recommendation online are affecting student college choices. PossibilityU, an innovative college guidance platform, and GroupLens, a research lab dedicated to recommender systems and online communities in the Department of Computer Science and Engineering at the University of Minnesota, Twin Cities, announced a research partnership to explore how college recommendations online can effect a broad range of student outcomes.
For the past 3 years, PossibilityU’s unique college guidance program has been matching high school students across the country with colleges that match their talents, aspirations and family budgets. The program features guided inquiry, data visualizations and personalized, Netflix-like recommendations—all designed to give students confidence in their choices. PossibilityU also features a blended-learning video curriculum created to help students and parents become better consumers of higher education.
“College recommendations are different from any other project we’ve taken on at GroupLens. This is the kind of project we love—one where research potential is large, multifaceted and one where the outcomes work toward a social good” said Dr. Joseph Konstan, co-director of the GroupLens lab.
At the White House and Department of Education’s Education Datapalooza in 2012 and 2014, PossibilityU was recognized for innovative use of open government education data and highlighted by College Summit students alongside Secretary of Education Arne Duncan. The Chronicle of Higher Education recently featured PossibilityU’s recommender system on its Data blog, and Brock Tibert has a good follow-up article from the perspective of enrollment management. In 2012, the Software and Information Industry Association’s Innovation Incubator awarded PossibilityU national top-10 honors for innovative ideas within small software companies. The educational technology industry has been most active around the college search and recommendation space, and in 2013 PossibilityU won a College Knowledge Challenge grant funded by the Bill & Melinda Gates Foundation in partnership with College Summit and Facebook. PossibilityU was also featured on Boston’s New England Cable News.
PossibilityU uses content-based item similarity metrics calculated using a version of K-nearest-neighbor. While traditional college search engines ask users to enter desired values (e.g., a college with 5,000-9,999 students in California), PossibilityU doesn’t require students to know relevant item features. The system asks for one or several college names, then displays a list of features which are both common to the set of input colleges and are unlikely to arise by chance, given the entire population of American colleges. It then displays other colleges that have properties similar to the calculated set of features. Under the hood, PossibilityU relies on an extensive collection of data from the US Department of Education (the IPEDS system).
Users control recommendations in several ways:
-
adding and removing colleges from the input set;
-
removing a feature (e.g., “higher number of students studying engineering”) from the automatically-calculated list of important features;
-
adding and removing academic fields (e.g., “business, management, and marketing”);
-
stating a preference to maximize the size and proportion of chosen academic departments or simultaneously maximize the diversity of academic options
“We are thrilled to have Dr. Konstan and the team at the GroupLens deepen the research base that informs our product”, said Betsy Peters, CEO of PossibilityU. “By closely studying how user experience, recommendations, and collaboration between students and their mentors work together online, we’ll be in better position to help scale the work that great college counselors do.”
PossibilityU is actively seeking schools and other student serving organizations interested in participating in this research beginning in Fall 2014. For more information contact betsy.peters@possibilityU.com or call 855-480-9126.
About Me
I’m a first-year Ph.D. student in GroupLens, and I’m working on exploration and matching in domains of high-cost sparse items with strategic user behavior. The college search displays significantly different properties than recommendation in book, movie, or music domains. There are relatively few colleges (about 2000 four-year colleges and 2000 two-year colleges in the United States) which are unevenly geographically distributed; item cost is quite variable and very high; traditional consumption- and memory-based ratings are not possible because students can’t try out and rate many colleges; and a number of other unusual or unique properties make college recommendation an exciting area of research.
As I continue work on college recommendation research at GroupLens, I’d love to hear from you. Drop me a line at @danjarratt or jarratt@cs.umn.edu.
About PossibilityU
PossibilityU is an education company dedicated to helping students become smart consumers of higher education. Our award-winning college guidance platform has been featured at the White House twice and was a winner of the Gates Foundation funded College Knowledge Challenge. Most importantly, it has been helping high school students across the country find the colleges that fit – academically, socially and financially – since 2010. PossibilityU features a Netflix-like recommendation engine, a 10-hour blended learning curriculum, and project management dashboards to help students and their mentors make great choices about choosing and financing college. To learn more about PossibilityU, visit www.PossibilityU.com.
