flexiblefullpage -
billboard - default
interstitial1 - interstitial
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

Smart Buildings | Jun 1, 2022

Taking full advantage of smart building technology

Drew Deatherage of Crux Solutions discusses where owners and AEC firms could do better at optimizing smart technology in building design and operations.

AEC Tech | Apr 19, 2022

VDC maturity and the key to driving better, more predictable outcomes

While more stakeholders across the AEC value chain embrace the concept of virtual design and construction, what is driving the vastly different results that organizations achieve? The answer lies within an assessment of VDC maturity.

Sponsored | BD+C University Course | Mar 24, 2022

Data-driven building design and successful project outcomes

Data-driven science, control systems and even journalism are in vogue today, reflecting the increasing reliance on real facts and figures—rather than experience or subjective opinions—to drive successful pursuits. In the architecture, engineering and construction (AEC) realm, the same trend is helping make project teams and buildings more successful. The ultimate goal is to enhance value through a process that predicts accurately the cost of a building—even if its architects may not see the construction begin until two or more years after the start of schematic design.

BIM and Information Technology | Mar 16, 2022

Construction still lags other industries in use of technology

JBKnowledge’s latest ConTech report asserts that while contractors have made some gains, too many don’t view IT as a priority, to their detriment.

Sponsored | BD+C University Course | Jan 10, 2022

Applied parametrics for façade designs and materials

Parametric modeling has proven an invaluable toolset that enables architects to test complex design concepts and organize large quantities of data into manageable work streams. Parametric iteration makes it possible to achieve unique solutions that require digital surface modeling and then apply them to interesting building materials that might previously have been considered unviable.

AEC Tech | Dec 16, 2021

Autodesk to Acquire Cloud Based Estimating Company ProEst

Autodesk, Inc. is acquiring ProEst, a cloud-based estimating solution that enables construction teams to create estimates, perform digital takeoffs, generate detailed reports and proposals and manage bid-day processes. Autodesk plans to integrate ProEst with Autodesk Construction Cloud, a comprehensive construction management platform connecting teams, data and workflows across the entire building lifecycle.

Sponsored | BD+C University Course | Oct 15, 2021

7 game-changing trends in structural engineering

Here are seven key areas where innovation in structural engineering is driving evolution.

AEC Tech Innovation | Oct 7, 2021

How tech informs design: A conversation with Mancini's Christian Giordano

Mancini's growth strategy includes developing tech tools that help clients appreciate its work.

boombox1 - default
boombox2 -
native1 -

More In Category




halfpage1 -

Most Popular Content

  1. 2021 Giants 400 Report
  2. Top 150 Architecture Firms for 2019
  3. 13 projects that represent the future of affordable housing
  4. Sagrada Familia completion date pushed back due to coronavirus
  5. Top 160 Architecture Firms 2021

 


Magazine Subscription
Subscribe

Get our Newsletters

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

Subscribe

Follow BD+C: