SPHHS students to compete in Five College ASA DataFest

March 30, 2016

On April 1 to 3, students from the Five Colleges (Amherst College, Hampshire College, Mount Holyoke College, Smith College, and the University of Massachusetts Amherst) will compete to see who can best analyze a complex dataset and attract the interest of employers at the 2016 American Statistical Association (ASA) Five College DataFest competition. The event, a unique collaboration between academia, students and industry, will be held at the Integrated Science Building on the UMass Amherst campus.

DataFest is an annual competition in which 30 teams of up to five undergraduate students work to reveal insights from a large and rich data set. The unique program takes data-analysis learning beyond what is normally encountered in a typical statistical science course by enabling the students to work with Big Data provided by a real client.

Last year, for example, students analyzed data from Edmunds.com, a car shopping website, using information about users’ advertisement success rates, purchases, frequency of visiting the site and other data to answer a variety of statistical questions.  In 2014, GridPoint provided a complex dataset that was used to model energy consumption for commercial buildings.  Students gleaned imaginative insights that might lead to decrease energy usage. This year's dataset will be unveiled on Friday, April 1st in a big reveal.

During the 48-hour event that begins Friday evening and concludes Sunday afternoon, each team competes head-to-head with all other teams for prizes in categories ranging from “Best Insight,” “Best Visualization” and “Best Use of External Data.” Each team presents its findings to a panel of judges—comprised of professors, data scientists, and representatives of the company or organization that provides the data set for the competition.

The student-competitors will also be showing their skills to various company and organization representatives who will be attending the event to offer advice to the competitors and identify the students for potential job opportunities.  The Five College event will be one of many taking place nationwide.

“While many participants enjoy DataFest as a friendly competitive event, it means much more to students nearing graduation and the company reps in attendance who are seeking to recruit new statistical talent,” says Rob Gould, UCLA faculty member and founding organizer of the ASA DataFest program. “In the relatively short history of DataFest, numerous students showcased their statistical skill during the event and simultaneously developed contacts with employers that have led to offers of full-time employment. Students who do well at DataFest are students who have proven that they can navigate the 'data deluge'. And this is very attractive to potential employers. "

Each year, the data and the challenge are different, but the common theme of making sense of big data—larger and more complex than the data sets undergraduate students usually encounter in a classroom—is carried over. The data set, which consists of real-world data that is of current interest to the providing organization or business, is not unveiled until the start of the competition so participating students cannot prepare in advance for the event.