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
| Jun 13, 2017
Accelerate Live! talk: Incubating innovation through R&D and product development, Jonatan Schumacher, Thornton Tomasetti
Thornton Tomasetti’s Jonatan Schumacher presents the firm’s business model for developing, incubating, and delivering cutting-edge tools and solutions for the firm, and the greater AEC market.
| Jun 13, 2017
Accelerate Live! talk: The future of computational design, Ben Juckes, Yazdani Studio of CannonDesign
Yazdani’s Ben Juckes discusses the firm’s tech-centric culture, where scripting has become an every-project occurrence and each designer regularly works with computational tools as part of their basic toolset.
| May 24, 2017
Accelerate Live! talk: Applying machine learning to building design, Daniel Davis, WeWork
Daniel Davis offers a glimpse into the world at WeWork, and how his team is rethinking workplace design with the help of machine learning tools.
| May 24, 2017
Accelerate Live! talk: Learning from Silicon Valley - Using SaaS to automate AEC, Sean Parham, Aditazz
Sean Parham shares how Aditazz is shaking up the traditional design and construction approaches by applying lessons from the tech world.
| May 24, 2017
Accelerate Live! talk: The data-driven future for AEC, Nathan Miller, Proving Ground
In this 15-minute talk at BD+C’s Accelerate Live! (May 11, 2017, Chicago), Nathan Miller presents his vision of a data-driven future for the business of design.
Big Data | May 24, 2017
Data literacy: Your data-driven advantage starts with your people
All too often, the narrative of what it takes to be ‘data-driven’ focuses on methods for collecting, synthesizing, and visualizing data.
AEC Tech | May 23, 2017
A funny thing may happen on the way to AI
As AI proves safe, big business will want to reduce overhead.
Building Technology | May 5, 2017
Tips for designing and building with bathroom pods
Advancements in building technology and ongoing concerns about labor shortages make prefabrication options such as bathrooms pods primed for an awakening.
BIM and Information Technology | Apr 24, 2017
Reconciling design energy models with real world results
Clark Nexsen’s Brian Turner explores the benefits and challenges of energy modeling and discusses how design firms can implement standards for the highest possible accuracy.
BIM and Information Technology | Apr 17, 2017
BIM: What do owners want?
Now more than ever, owners are becoming extremely focused on leveraging BIM to deliver their projects.