With the rise of big data, marketers are finding new and better ways to analyze and predict consumer behavior—and Marina Girju is preparing DePaul students to do the same.
“We have a hands-on approach. For every model that I’m introducing, I also have a project where the students have to apply the model to the data set. They put everything in the perspective of the consumer or business so we can understand how the analysis is going to influence all of the parties involved,” says Girju, assistant professor of marketing in the Driehaus College of Business.
The term “big data” refers to the collection of large, complex data gathered through multiple methods. For marketing, data can come from point-of-sale scanners at a store, loyalty cards or online shopping, among other sources.
“The data can be very overwhelming—not only the size, but also the richness,” Girju says. “Most data sets have at least 100 variables that explain consumer behavior, and in my course, it’s usually over 300. You can cut it in a million ways and get a million answers.”
Girju knows about putting data into context. Before joining DePaul in 2012, she worked for TNS, a leader in consumer market research, as a data analyst. Her job for the company’s client Frito-Lay was to study the data generated by thousands of U.S. consumers who recorded details about their snacking habits. Girju and her co-researchers then developed DemoImpact, a forecasting model for predicting snack consumption for hundreds of snacks in dozens of categories.
In her own research and in the classroom, Girju continues to examine the connection between big data and business strategy. She gets her undergraduate and graduate students excited about research and analytics by engaging them in real-world projects. No matter the class, Girju reaches students by combining the theoretical with the practical. “A piece of analysis is important, but it is so much better if it’s actually put in context of trends and challenges in the industry,” she says.