The Capstone Project is a degree requirement for students in our data analytics program and is designed so that both the students and capstone partners gain experience working on real-life data- and analytics- related problems. Capstone partners and students engage with key problems the company needs to solve.
Students work in teams of two to three with a faculty advisor and business partner to address a business problem. Teams may identify their own company with a business problem, or teams may pick a data analytics problem supplied by MScA industry research partners.
More Capstone Projects from Our Graduates
COPD Readmission And Cost Reduction Assessment
UChicago Analytics students built data models and evaluated them across different frameworks and determined that the resulting model is capable of rank-ordering readmission risk and allowing for flexibility in applying interventions to prevent readmission.
An NFL Ticket Pricing Study
Optimizing Revenue Using Variable and Dynamic Pricing Methods
UChicago Analytics students find a way for an NFL team to implement ticket pricing that responds to changing factors and gives the team the chance to fill more seats.
Image Recognition to Identify Yoga Poses
Master of Science in Analytics students built an app that uses a one-step neural network to examine images of yoga poses and recognize the poses in order to provide feedback to the app's yoga-practicing user.
Using Image Recognition to Measure the Speed of a Pitch
One capstone team developed an app that applied image recognition algorithms to measure the speed of a pitched baseball. Their app captured video, isolated the pitched ball, the calculated the velocity of the pitch and displayed this measurement so that app users would be able to measure the speed of a pitch with their smartphones.
Real-Time Anomaly Detection within Credit Card Transactions
Credit card fraud puts consumer's identities at risk while credit card providers are forced to cover fraudulent charges. A team of analytics students went above and beyond to carefully study this problem: they created synthetic data that represented a large population of credit-card users and were able to build a model that catches credit card fraud in real time.