If AI-driven machines can defeat the world’s greatest chess players and, even more improbable, the globe’s premier Go strategist, what chance does a college dropout have against machine learning technology? Slim to none, predicts one university research director.
Sudha Ram, a Professor of Management Information Systems and Director of the Center for Business Intelligence and Analytics with the University of Arizona, is leading a research project at UA that aims to prevent college dropouts from dropping out in the first place.
Ram’s efforts are nothing new for U.S. colleges and universities. Many schools use predictive analytics to help reduce freshman attrition rates. UA, for example, already tracks some 800 data points toward this effort. What makes Ram’s research unique are the types of data being collected and how those metrics are analyzed to more effectively identify at risk students.
The first several months of freshman year are the most harrowing for students. Colleges and universities know this. They also know that there are a number of early indicators for students who are most at risk for leaving after their first year. Most obvious are first-semester grades, financial aid activity, and students’ participation in course management systems. But even that information may come too late to make a difference. (Research suggests that most freshman make the decision to leave school within the first 12 weeks.)
Less evident but infinitely more powerful, says Ram, are social- and behavioral-related metrics such as shrinking social networks, fewer social interactions, and less-established routines.
Ram’s stockpile of student activity data comes from the university’s ID card tracking system, which collects information on everything from what students buy and eat to the buildings and spaces they frequent. Using large-scale network analysis and machine learning techniques to crunch three years worth of ID card usage data, Ram is able to piece together complex behavioral patterns for both student groups and individuals.
For example, if student A, on multiple occasions, uses her ID card at the same location and time as student B, it stands to reason there is social interaction between the two. When extrapolated over time, detailed behavioral and social patterns emerge.
By tracking changes to these patterns over time, Ram has been able to accurately predict freshmen dropouts at an 85-90% rate, up from the university’s current success rate of 73% using traditional metrics.
The findings show promise for the use of machine learning methodologies and big data analytics in the AEC industry and real estate sector. For example, a similar approach could be applied to commercial office buildings, to identify tenants that are most at-risk for not renewing their lease.
Related Stories
BIM and Information Technology | May 20, 2016
AIA and Autodesk introduce new feature to automate 2030 Commitment reporting data
The new automated connection will allow the more than 350 AIA 2030 committed firms to report their project and portfolio performance to the DDx directly from Autodesk Insight 360.
AEC Tech | May 10, 2016
Thornton Tomasetti launches new tech company
TTWiiN initially features six products and will add more via its own incubator.
Sponsored | BIM and Information Technology | May 10, 2016
Advanced laser scanning technology supports data collection and modeling efforts for Missouri’s Iatan 1 Power Plant
For the installation of a new heat exchanger, the power division of Black & Veatch contracted an engineering firm to laser scan the site, make a piping model in Autodesk® Revit®, and export it into AutoCAD® to deliver results.
AEC Tech | May 9, 2016
Is the nation’s grand tech boom really an innovation funk?
Despite popular belief, the country is not in a great age of technological and digital innovation, at least when compared to the last great innovation era (1870-1970).
Big Data | May 5, 2016
Demand for data integration technologies for buildings is expected to soar over the next decade
A Navigant Research report takes a deeper dive to examine where demand will be strongest by region and building type.
BIM and Information Technology | May 2, 2016
How HDR used computational design tools to create Omaha's UNO Baxter Arena
Three years after writing a white paper about designing an arena for the University of Nebraska Omaha, HDR's Matt Goldsberry says it's time to cherry-pick the best problem-solving workflows.
Drones | Apr 25, 2016
The Tremco SkyBEAM UAV is the first to be approved by the FAA for nighttime commercial operation
The SkyBEAM UAV is used for identifying energy leaks, rooftop damage, deteriorating façades, and safety issues without requiring scaffolding or cranes.
BIM and Information Technology | Apr 21, 2016
U.K. imposes BIM requirement on government projects
U.S. unlikely to follow suit.
AEC Tech | Apr 15, 2016
Should architects learn to code?
Even if learning to code does not personally interest you, the growing demand for having these capabilities in an architectural business cannot be overlooked, writes computational design expert Nathan Miller.
Building Tech | Apr 12, 2016
Should we be worried about a tech slowdown?
Is the U.S. in an innovative funk, or is this just the calm before the storm?