Partner
University of Rochester – Office for Global Engagement
Industry
Higher Education
Objective
Build objective and time dynamic framework for data-based ranking of universities
The Opportunity
University of Rochester’s Office for Global Engagement sought a data-driven university ranking methodology that more accurately assesses the strengths and weaknesses of research institutions in the U.S. and worldwide. Current university ranking methodologies rely upon reputational data extracted from individual surveys of populations of interest, often favoring a few select institutions due to intrinsic human bias. At the same time, the rankings tend to supply a static view of the dynamic academic landscape.
The Challenge
RDSC had to replace subjective survey questionnaires with tangible datasets (publications, grants, patents, and clinical trials) to make the ranking system reflect temporal developments in the global academic research landscape. In order to accomplish that goal, RDSC scientists had to pursue a method that incorporates more data, including ongoing research trends, and avoids the human bias reflected in popular university rankings.
“There is a need within higher education to validate and qualify rankings through the lens of comprehensive scholarly productivity. The application of machine learning methods to curated research databases holds promise as a potential solution.”
The Solution
RDSC employed supervised and unsupervised machine learning, deep learning and long-short term memory prediction models. They utilized the Dimensions dataset, a collaborative global data platform that catalogs publications, grants, patents, and clinical trials, as well as the connections among them.
- First, RDSC queried the Dimensions dataset across 22 fields of research to build global- and institution-level temporal research trends.
- Next, RDSC compared university research data, across schools and across time, to determine whether an institution is ahead, on par, or behind a given reference trend.
- Finally, RDSC Scientists leveraged long-short-term memory networks (LSTM) to predict the future path of research trends. This technology allows the ranking model to anticipate the evolution of a given institution’s standing in a particular field, and factor this
