Capstone Projects
Capstone projects are one of the most important components of the MIDS program. These year-long projects integrate students into world-class interdisciplinary research projects that can solve real-life problems and be significantly advanced through data science.
Benefits of Capstone Projects
- Get real-world experience.
- Translate what you’ve learned in the classroom.
- Make substantial contributions to complex projects.
“Our team built an effective animal classification model for the NGO Saving Nature for the purpose of providing a solution to largely reduce manual work on image labeling. This would help Saving Nature get access to essential data more quickly, leaving scientists more time to study animal species occurrence, populations, and behavior, and evaluate the effectiveness of restoring nature and take actions to protect them. Our pre-trained deep learning models will be placed on the AWS instance and we created a very simple web interface where our clients can upload new images, select the type of the classification models to run, and get back the deep learning models’ predictions.“
Yingyu Fu, MIDS 2020
What’s Involved
Capstone projects have oversight from faculty in departments across Duke with research interests and expertise aligned with the project. However, each MIDS student must achieve a specific outcome of interest for an outside party (such as a company, government agency, or nonprofit) as part of the greater research and give a final presentation with an accompanying white paper about the implications of that outcome.
To ensure MIDS students complete their projects successfully, they will attend workshops and complete assignments throughout the second year that provide guidance, practice, and feedback about students’ teamwork, project management, communication plan, and overall progress in relation to the project.
The final deliverables will be evaluated by MIDS core faculty and relevant outside stakeholders on multiple dimensions including students’ ability to communicate effectively to a diverse audience, computational strategy, and creativity.
“We know when companies are hiring data scientists, they are looking for experience. They understand people learn things in classes, but they want to hire people who understand how to actually put together a data project.”
Robert Calderbank, Co-Director
