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
| Jan 31, 2014
LEGO, Google partner to develop 3D modeling tool for LEGO structures
The free tool, called Build, allows Chrome users to create virtual 3D structures using any shape and color in the LEGO catalog.
| Jan 30, 2014
See how architects at NBBJ are using computational design to calculate the best views on projects [video]
In an ideal world, every office employee would have a beautiful view from his or her desk. While no one can make that happen in real life, computational design can help architects maximize views from every angle.
| Jan 15, 2014
6 social media skills every leader needs
The social media revolution—which is less than a decade old—has created a dilemma for senior executives. While its potential seems immense, the inherent risks create uncertainty and unease.
| Jan 12, 2014
CES showcases innovations: Can any of these help you do your job better?
The Consumer Electronics Show took place this past week in Las Vegas. Known for launching new products and technologies, many of the products showcased there set the bar for future innovators. The show also signals trends to watch in technology applicable to the design and building industry.
| Jan 12, 2014
5 ways virtual modeling can improve facilities management
Improved space management, streamlined maintenance, and economical retrofits are among the ways building owners and facility managers can benefit from building information modeling.
| Dec 31, 2013
Top 10 blog posts from 2013
BD+C editors and our contributors posted hundreds of blogs in 2013. Here's a recap of the most popular topics. They include valuable lessons from one of the first BIM-related lawsuits and sage advice from AEC legend Arthur Gensler.
| Dec 31, 2013
BD+C's top 10 stories of 2013
The world's tallest twisting tower and the rise of augmented reality technology in construction were among the 10 most popular articles posted on Building Design+Construction's website, BDCnetwork.com.
| Dec 17, 2013
IBM's five tech-driven innovation predictions for the next five years [infographics]
Smart classrooms, DNA-based medical care, and wired cities are among the technology-related innovations identified by IBM researchers for the company's 5 in 5 report.
| Dec 16, 2013
Is the metal building industry in a technology shift?
Automation is the future you can’t avoid, though you may try. Even within the metal building industry—which is made up of skilled tradesmen—automation has revolutionized, and will continue revolutionizing, how we work.
| Dec 10, 2013
16 great solutions for architects, engineers, and contractors
From a crowd-funded smart shovel to a why-didn’t-someone-do-this-sooner scheme for managing traffic in public restrooms, these ideas are noteworthy for creative problem-solving. Here are some of the most intriguing innovations the BD+C community has brought to our attention this year.
