Smith Teams Succeed at Five College DataFest

Winners of Best in Show at this year's Five College DataFest was Smith team DataBest (front row from left) Zainab Aqdas Rizvi '18, Subashini Sridhar '18J, Ji Young Yun '18, Ji Wong Chung '18 and Van Nguyen '18.

This year’s Five College DataFest was a “sweet victory” for Smith, as the college won three of six awards at the fourth annual event.

Awards for Smith teams went to:

  • Best in Show—Zainab Aqdas Rizvi ’18, Subashini Sridhar ’18J, Ji Young Yun ’18, Ji Won Chung ’19 and Van Nguyen ’18 of team DataBest
  • Best Statistical Interpretation—Zixian Li ’19, Angie Dinh ’17, Abby Doctor ’17, Erina Fukuda ’18 and Raeesa Alam ’19J of team Normally Distributed
  • Best Business Insight—Isabella Zhu ’20, Cas Sweeney ’19, Sarah Abowitz ’20 and Garcia Sun ’20 of team Standard Divination.

Assistant Professor of Statistical and Data Sciences Ben Baumer, co-organizer of Five College DataFest, says this year’s showing in the yearly data-analysis competition was a happy event for Smith.

“We won the Best in Show prize at the first two DataFests, but were shut out of the awards completely last year,” Baumer says. “This year, Smith teams won Best in Show again, as well as two other prizes.”

This year was also a big one for Five College DataFest, which drew a record 130 participants. Five College DataFest is tied for the third largest DataFest competition in the nation, along with Ohio State and Purdue University. (UCLA and Duke University have the largest events.)

Sponsored by the American Statistical Association (ASA), DataFest is both a competition and a celebration of big data analysis. The event invites undergraduate students with computer, statistical or data science backgrounds to take part in a 48-hour-long, big-data analysis project.

Ji Won Chung ’19, a member of Smith’s winning DataBest team, says the event is an opportunity to meet new people and bond with teammates.

“Participating in DataFest allowed me to expand my perception of data by looking at the presentations of the other groups,” Chung says. “It also helped teach me how to work well in a group under pressure.”

Fellow Databest member Zainab Aqdas Rizvi ’18 says the team aspect was her favorite part of the competition.

“We all had really different strengths that came together well in our final project,” she says. “Some people were good at visualization, some were good at code, others at data analysis, and I believe our final project really represented our group’s diverse skills.”

While competition adds to the excitement of DataFest, Baumer says the event is primarily a learning experience.

“For many students, this is their first time working with a real, large, complex, messy data set, with no structured questions or pre-defined tasks,” he says. “This experience mimics what graduates are likely to see in the real world. Many students have remarked that they learned as much during DataFest as they did in a full-semester class—or even more.”

Baumer adds that DataFest is also a great experience to talk about in a job interview because it requires working with a team on a big, open-ended deadline project.

Regardless of the outcome of the competition, DataFest offers participants a chance to share in their love of computing, Baumer says.

“At the end, everyone is exhausted, but most people are feeling alive and energized at the same time,” he says. “Win or lose, the smiles on students’ faces are priceless.”