Twenty-eight Boston University (BU) undergraduate and graduate students — data science, computer science, and political science majors — recently teamed up with corporate mentors at MassMutual for the Spring 2024 Data Days for Good (DD4G) event. Students worked in teams to explore the following questions: Is there a discrepancy between participation rates of males and females in technology-focused majors at Boston University? Are there correlations between employee satisfaction and organized labor? How has coverage of the Black community in the media changed over time? What are the causes of equitable land access in the commonwealth?
The intensive four-day event is part of an ongoing collaboration between MassMutual and the Faculty of Computing & Data Sciences (CDS) at Boston University. For the second year in a row, CDS data science students and other majors partnered with MassMutual data scientists, data engineers, and software engineers to work on data-focused projects for nonprofit and civic tech partners in greater Boston.
According to Ziba Cranmer, director of BU Spark!, an innovation incubator embedded within CDS, the Data Days for Good mentorship program provides an invaluable opportunity to immerse Boston University students into a data-driven, professional environment.
“Mentorship is especially important in emerging disciplines like data science where the field is evolving rapidly,” said Cranmer. “This mentorship program provides our students with access to information about the professional opportunities that will be available to them and the skills they need to develop to be successful.”
MassMutual Data Scientist and Data Days for Good Mentor Audrey Bertin said she looks forward to working with student mentees because they bring a strong sense of curiosity and are excited to learn.
“Data Days for Good is also such a great opportunity for students to practice on real-world data and projects and start to build networking connections in industry,” Bertin said. “Having group work, the opportunity to practice talking face to face with clients, and, for some projects, being required to modify existing code, rather than start from scratch, prepares the students for what work is really like after graduation.”
Projects and the Student Experience
Hannah Choe, CDS’25, worked on the Racial Bias in Media project. The team analyzed published news stories spanning over a ten-year period. The goal was to assess news coverage of the Black community in Boston and evaluate the changes in the type of coverage over time in terms of volume, sentiment, and more.
“I really enjoyed interacting with my team and mentors. While there were many roadblocks in the progress of the project, our group’s mentor was very helpful brainstorming solutions, and overcoming the challenges as a team was truly rewarding,” she said.
Naman Nagaria, CDS’26, and his team examined land use in Massachusetts using data from Hampden County’s Registry of Deeds to understand patterns of land use restrictions in the commonwealth.
“I liked how well my team gelled together, and I enjoyed how we were able to put our skill sets to use when working on the client project but at the same time learn new things together as a team,” he said. See project details below.
Why Mentorship Matters
Bahar Bazargani, data science product manager and returning mentor, also noted the “enthusiasm, dedication, and collaborative spirit” of the BU student teams, makes the experience of being a mentor a rewarding one.
“Mentorship is invaluable for both mentors and mentees, fostering mutual growth, skill development, and personal connections,” Bazargani said. “It offers mentors the opportunity to share knowledge and experience while empowering mentees to navigate challenges and realize their potential.”
To learn more about BU Spark! and the Data Days for Good program.
The following is an overview of the all Spring 2024 Data Days for Good Projects:
BU Tech Majors Undergraduate Experience Survey Analysis: Conduct an analysis of the BU tech majors survey (900+ responses) to understand the experiences of BU undergraduate tech majors across different departments and backgrounds over time, showcasing findings with key visualizations and shiny apps.
Client: BU DEI Tech Collective
Understanding Employment Discrimination and Organized Labor: With recent spikes in the number of union elections, this project aimed to identify how efforts to organize affect patterns of employment discrimination reporting in California by accessing public data on 80,000 employment discrimination reports, employer information, and union elections. These large, messy datasets were merged with a strategic process, including the development of a replicable matching plan, ultimately creating a cohesive dataset that can be used for the next phase of analysis.
Client: The People, Organizations, and Power Lab at BU
Land Use in Massachusetts: Apply large language models to data on land ownership records from Hampden County’s Registry of Deeds to understand patterns of land use restrictions and implications for equitable access to land in the Commonwealth.
Client: Longmeadow Historical Society
Racial Bias in Media: This project assessed news coverage of the Black community in Boston by the Boston Globe using LexisNexis data over a ten-year period between 2010-2020 to understand how it has changed over time in terms of volume, topics covered, sentiment, and comparisons to other geographies. Using named entity recognition methods (geographic locations, organizations, company names, points of interest, etc.), this analysis assigned a geographic location and the associated demographics of that location based on data from the U.S. Census.
Client: BU Spark! partner
MassMutual Mentors
Bahar Bazargani | Audrey Bertin | Michael Bessey | Tim Casey | Carla Davis | Vijay Raju Gurusamy | John Martinez | Joseph Merrigan | Anisha Pai | Naren Chowdary Ravilla | Mary Ellen Sullivan | Tianyu Wu
Boston University Student Mentees
Roamah Baray (CAS/CDS’24) | Naomy Bopela (CS’26) | Jack Campbell (MSDS’24) | Mason Carlucci (CDS’26) | Hannah Choe (CDS’25) | Daniel Doh (CDS’25) | Sahir Doshi (CDS’24) | Vijay Fisch (CDS’26) | Zachary Gou (CS’24) | Valentina Haddad (CS’25) | Ryan Long Hei Ko (CDS'24) | Sindhuja Kumar (CDS’25) | Alessandra Lanz (CS’26) | Catherine Liu (CS’26) | John Markowicz (CDS’24) | Maisha Miah (CS’24) | Naman Nagaria (CDS’26) | Oghenerukevwe (Rukevwe) Omusi (CDS’25) | Riya Parikh (CDS’25) | Abdul Rafay (CDS’26) | Ishan Ranjan (MSDS’24) | Karrington Riley (CDS’26) | Derinell Rojas (CS’25) | Neeza Singh (CDS’25) | Anush Veeranala (MSDS'24) | Bohan Wang (MSDS’24) | Yujia (Stella) Zhai (CAS'25) | Xinyu (Cindy) Zhang (MSDS’24)
Student Voices: Technical Skills Development & Key Takeaways
Karrington Riley, CDS’26:
“I learned how to clean data using cleanco and pandas. I learned how to apply the FuzzyWuzzy algorithm to test the validity of strings, and I learned the true value of teamwork.”
Mason Carlucci, CDS’26:
“I learned how to break out into groups and tackle a coding assignment and presentation and how to communicate with an actual client.”
Cindy (Xinyu) Zhang, MSDS’24:
“I enjoyed drawing flow charts to break down the process, building websites [that] interact with backend code, and collaborating with others.”
Sindhuja Kumar, CDS’25:
“I thoroughly enjoyed developing the final product, which included endless testing, debugging, and brainstorming sessions.”