Charles Liu

“I hope to continue my research on machine learning and data mining and collaborate with faculty in different areas.”

Business Analytics & Statistics - Faculty

Charles Liu is interested in developing algorithms that can be used for problems and applications across business disciplines.

“Theoretically, algorithms can be applied to a problem in any area, from finance to marketing,” he says. “When you’re trying to address similar problems, you can apply the same methodology.”

He earned a doctorate in management information systems at Rutgers University and spent the next four years working on research and teaching master’s level data mining courses at Philadelphia’s Drexel University. Haslam hired Liu in 2019 as an assistant professor.

“I hope to continue my research on machine learning and data mining and collaborate with faculty in different areas,” he says. “I’m also looking forward to teaching data mining courses and working with students on research projects.”

One of Liu’s recent research projects looks at sequential pattern analysis.

“It starts with identifying the crucial patterns in sequential data,” he says. “We used this approach to map out the buying path followed by customers in a B2B marketing application.”

When marketers are aware of a customer’s position, they can help foster progression toward making a decision. The goal is to increase the conversion rate and decrease the time involved.

“Using our algorithm to give customers the most relevant information, the conversion efficiency can be improved significantly,” he says. “A sale that might have taken three months could take three weeks.”

Liu’s collaborative paper was published in IEEE Transactions on Knowledge and Data Engineering.

His research toward developing an algorithm that assesses risks for investors on peer-to-peer lending markets appeared in the European Journal of Operational Research. INFORMS Journal on Computing published another of Liu’s papers, from a research project that analyzed public transportation records in big cities.

“We used data mining algorithms to identify noteworthy transportation patterns, which can be used for optimizing the efficiency of public transportation services,” Liu says.