Let’s make a deal
KSU math professor trains students for the real world
By Shawn Jenkins
Call it…
Georgia
(Oct 28, 2009) —
KSU math professor trains students for the real world
By Shawn Jenkins
Call it serendipity.
Jennifer Priestley, an associate professor of applied mathematics at Kennesaw
State University, was beginning to see an unmet need in her department for a class
in financial modeling — for credit scoring in particular. “I had been thinking about
building a course and coincidentally was having coffee with Brian Stone, the chief
risk officer with CompuCredit,” she said.
Stone told Priestley how the KSU grads he hired saved his Atlanta-based
company roughly $60,000 in training costs thanks to their immediate savvy with Statistical
Analysis Software (SAS), CompuCredit’s primary tool.
Stone wanted to know if there was some way he could contribute to her
program for sending such well-prepared people. “What can you guys use?” he asked.
Priestley’s answer: data.
What Priestley knew from her own real-world experience is that KSU’s applied
stats program would be carving its niche by doing statistical analysis using real-world
data representing actual people, not the antiseptic educational data sets they had
been working with.
When she finished her M.B.A. in finance at Penn State in 1990, Priestley
went to work for AT&T in New York and quickly moved to the credit card division, where
she managed various aspects of their Universal Credit Card portfolio.
After a stint doing business development for MasterCard in New York, she
moved to London to take a position with Visa. “It was kind of a perfect storm,” she
explained. “They had a VP position open and they needed someone who had a credit-based
background instead of a debit-based background, because most of Europe at that point
was debit-based.”
Priestley worked with Scottish and Irish banks, helping them transition
from debit-based portfolios to credit-based. “They didn’t have the equivalent of TransUnion,
Equifax and TRW, so I was applying a quantitative scoring system for them to determine
people’s credit-worthiness,” she said.
“When my husband and I moved back to the United States, I was burned out.
I had a million frequent-flyer miles by the time I was 35. So, I went back and got
my doctorate at Georgia State. Now I’ve settled in as a professor at Kennesaw State
University, and I’m very happy.”
Priestley’s chance exchange with Stone opened the door to the solution
for the one thing about her job that made her less happy.
“I felt like we were doing our students a disservice in giving them data
sets that were so clean and textbook,” she said. “We were leading them down the primrose
path of thinking that data really looks like this — but it doesn’t.”
After legal review and stripping out any private, identifiable information,
CompuCredit provided Priestley’s statistics 7900 class (Credit Risk Modeling Using
Binary Logistic Regression) with a massive data set from Equifax consisting of 10
million observations, representing 10 million real people and approximately 355 pieces
of information for each person.
“We were given around 1 million observations in our group’s subset and
it was messy — very sparse, lots of missing data and lots of coding issues,” said
Erin O’Connor, a master’s student in Priestley’s statistics 7900 course. “That’s what
it’s going to be like. If you have one person and one missing variable when you run
the analysis, SAS will throw that person out. So, in this job market, it will come
down to someone who knows the theory and someone who has worked with a real-world
data set. We have that leg up.”
When applied statistics was offered as a minor three years ago, Priestley
said “there were some who snickered” at the thought that undergraduates would seek
out 3000- and 4000-level statistics classes to fill in their interdisciplinary electives.
“Well, guess what? We have anywhere from 150 to 200 students who are declared
undergraduate minors in statistics in any given semester,” she said. “I would put
those numbers against any minor on campus any day.”
Much of that success Priestley attributes to the high demand for KSU’s
applied stats skill set in the workplace.
“We don’t just derive formulas,” she said. “These courses are contextual
and project-based, not just theoretical. And Kennesaw State is the only institution
in Georgia that offers undergraduates training in SAS. Ninety-five percent of Fortune
500 companies use it.
“In this economy, we have a 100 percent placement rate for our master’s
students, and our undergrads are in demand too. I hear people talk about how there
are no jobs out there. You don’t hear our students say those words.”
A leader in innovative teaching and learning, Kennesaw State University offers undergraduate, graduate and doctoral degrees to its nearly 43,000 students. With 11 colleges on two metro Atlanta campuses, Kennesaw State is a member of the University System of Georgia. The university’s vibrant campus culture, diverse population, strong global ties and entrepreneurial spirit draw students from throughout the country and the world. Kennesaw State is a Carnegie-designated doctoral research institution (R2), placing it among an elite group of only 6 percent of U.S. colleges and universities with an R1 or R2 status. For more information, visit kennesaw.edu.