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
| Aug 11, 2010
Polshek Partnership unveils design for University of North Texas business building
New York-based architect Polshek Partnership today unveiled its design scheme for the $70 million Business Leadership Building at the University of North Texas in Denton. Designed to provide UNT’s 5,400-plus business majors the highest level of academic instruction and professional training, the 180,000-sf facility will include an open atrium, an internet café, and numerous study and tutoring rooms—all designed to help develop a spirit of collaboration and team-oriented focus.
| Aug 11, 2010
Callison, MulvannyG2 among nation's largest retail design firms, according to BD+C's Giants 300 report
A ranking of the Top 75 Retail Design Firms based on Building Design+Construction's 2009 Giants 300 survey. For more Giants 300 rankings, visit http://www.BDCnetwork.com/Giants
| Aug 11, 2010
ASHRAE releases free BIM introductory guide
A newly released guide from ASHRAE on building information models and building information modeling (BIM) serves as a resource for professionals considering BIM tools and applications for their businesses. According to "An Introduction to Building Information Modeling," BIM is “a digital representation of the physical and the functional characteristics of a facility.” Unlike 2D or 3D CAD, BIM software utilizes intelligent objects to create models.
| Aug 11, 2010
BIM research: New IPD document quantifies savings, shows obstacles
The American Institute of Architects and the AIA California Council have released the results of “Integrated Project Delivery: Case Studies,” a collection of six studies that showcases the process changes and efficiencies of completed building projects that utilized and implemented IPD. IPD is a construction project model in which owners, design professionals, and general contracto...
| Aug 11, 2010
Take the hassle out of managing subcontractors
As general contractors look to technology for an edge in the slowing commercial construction market, Web-based bidding programs are helping them to connecting bid information, subcontractors, and proposals. A 2008 survey by the Construction Financial Management Association found that 62% of general contractors participated in Web-based construction bidding vs.
| Aug 11, 2010
Wisconsin becomes the first state to require BIM on public projects
As of July 1, the Wisconsin Division of State Facilities will require all state projects with a total budget of $5 million or more and all new construction with a budget of $2.5 million or more to have their designs begin with a Building Information Model. The new guidelines and standards require A/E services in a design-bid-build project delivery format to use BIM and 3D software from initial ...
| Aug 11, 2010
News Briefs: GBCI begins testing for new LEED professional credentials... Architects rank durability over 'green' in product attributes... ABI falls slightly in April, but shows market improvement
News Briefs: GBCI begins testing for new LEED professional credentials... Architects rank durability over 'green' in product attributes... ABI falls slightly in April, but shows market improvement