- Team Watergrass
Student Participants: Brendan O’Connor, Conor O’Regan, Riley Gardner, Vineeth Appala
Watergrass offers fundraising, membership, and volunteerism data management services for growing nonprofits concerned with environmental conservation and protection. The students have taken on this project to draw valuable insights from 15+ years of data from ~30 organizations. They have accomplished this by developing individual dashboards for each organization, an aggregated dashboard for Watergrass employees, and engineering a predictive model. As a result, each organization that works with Watergrass will be able to investigate specific questions they have pertaining to their donors/fundraising campaigns and Watergrass will be able to provide a high-level overview of the volunteerism landscape.
- Team EBC
Student Participants: Anthony Morin, Bryson Herring, Carter Mercer
EB Capital Markets generates its current financial market reports by performing all of its data collection manually and wanted a more interactive client experience. This team evaluated the leading financial APIs and web hosting services to find the best value for EBC where they automated EBC’s data collection via IEXCloud and AlphaVantage and created a proof-of-concept website for clients. EB Capital now has an automatically populated database, and a proof-of-concept website that can be further developed and launched.
- Team JNJ
Student Participants: Karen Zhang, Nisha Naugain, Tamilazhagan Ezhil
J&J’s medical devices section deals with bone replacement surgeries focused on Knees and Hips. Inaccurate prediction of part sizes increases cost in production, inventory and supply chain. This team was assigned with tasks of generating insights from the sample dataset and building machine learning models with higher prediction accuracy. The team accomplished the tasks by building dashboards which showcase quantitative insights on top performers across different variable and identified potential business expansion opportunities. The team also build Machine Learning models which are able to predict the required part size that reduces the overall cost for this department.
- Team UNH
Student Participant: Jon Olson
Currently, all the incoming freshmen in the Paul School of Business and Economics are being assigned to their required freshmen classes manually by advisors. This team was tasked with finding a way to assign students more efficiently to predetermined "bundles" of classes. Through a combination of front-end data validation in Excel and an R script that performs the assignment function, the team was able to engineer a process that assigns roughly 90% of the students and eliminates much of the time spent on this tedious task.