Currently Reading

Machine learning takes on college dropouts

BIM and Information Technology

Machine learning takes on college dropouts

Many schools use predictive analytics to help reduce freshman attrition rates.

By David Barista, Editorial Director | June 12, 2018
Students lined up against a wall
Students lined up against a wall

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

AEC Tech | May 24, 2021

Digital twin’s value propositions for the built environment, explained

Ernst & Young’s white paper makes its cases for the technology’s myriad benefits.

AEC Tech | Mar 4, 2021

The Weekly show, March 4, 2021: Bringing AI to the masses, and Central Station Memphis hotel

This week on The Weekly show, BD+C editors speak with AEC industry leaders about the award-winning Central Station Memphis hotel reconstruction project, and how Autodesk aims to bring generative design and AI tools to the AEC masses.

AEC Tech | Jan 28, 2021

The Weekly show, Jan 28, 2021: Generative design tools for feasibility studies, and landscape design trends in the built environment

This week on The Weekly show, BD+C editors speak with AEC industry leaders from Studio-MLA and TestFit about landscape design trends in the built environment, and how AEC teams and real estate developers can improve real estate feasibility studies with real-time generative design.

AEC Tech | Nov 12, 2020

The Weekly show: Nvidia's Omniverse, AI for construction scheduling, COVID-19 signage

BD+C editors speak with experts from ALICE Technologies, Build Group, Hastings Architecture, Nvidia, and Woods Bagot on the November 12 episode of "The Weekly." The episode is available for viewing on demand.

Smart and Resilient Cities | Oct 26, 2020

World’s first smart building assessment and rating program released

The SPIRE Smart Building Program will help building owners and operators make better investment decisions, improve tenant satisfaction, and increase asset value.

BIM and Information Technology | Oct 8, 2020

4 challenges of realizing BIM's value for an owner

In recent years, we have found our consulting practice engaging more and more with owners that are questioning the value of BIM and how they can make use of potentially data-rich BIM assets.

AEC Tech | Feb 5, 2020

BIM London: A glimpse of BIM discussions across the pond

Digital twin, ISO standards, blockchain, and data were the hot topics at the recent The Digital World: BIM event.

Building Technology | Mar 6, 2019

Australia’s prefab construction sector is trying to break out from its 'getting there' stage

A paper by Deloitte looks back at an origin case study. But the country has yet to develop a fully formed industry.

BIM and Information Technology | Jan 18, 2019

BIM: Sharing is caring

Sharing of and reliance on BIM data is central to the idea that BIM will lead to a more efficient, more economical, and more collaborative construction process.

BIM and Information Technology | Jan 10, 2019

'BIM to AR' comes to the masses

Could new technology that simplifies the transfer of BIM models to augmented reality push AEC firms to go all in on extended reality?

More In Category

Magazine Subscription

Get our Newsletters

Each day, our editors assemble the latest breaking industry news, hottest trends, and most relevant research, delivered to your inbox.


Follow BD+C: