Capstone Project

Data Science Capstone Guidelines

Every student who majors in data science must show mastery of the data science cycle (see below). The work of this capstone project will culminate to an at an in-person poster session at the end of April. The presentation may be derived from an internship; a thesis; a course project; independent study; participation in the summer research program; or another experience. Students are expected to spend time developing the presentation beyond the time spent on the project itself. This is also a time for students to step back and reflect on the data science process as a whole, including data ethics and communication. Each student should produce a github repository where they upload slides and any other files used for the project, with a README and other documentation. If the data cannot be posted for any reason, students should post synthetic data demonstrating the data format. If the project was originally conducted in a group, the student should take ownership of a component that follows the steps in the data science cycle. If the project focuses on methods development, the presentation should demonstrate an application of the methods. Students should discuss their plans for the capstone with a Data Science advisor at an advising event well before the poster session. 
 
Linked here are examples of past capstone projects.
 
Please see last spring's capstone schedule below:

Spring 2022:

  • Seniors have been assigned to capstone advisors, usually not the major advisor. Juniors who wish to participate this year should alert us right away so that we can assign an advisor.
  • Fri, Jan 28: Each participating student submits a structured abstract, using this template. Abstracts should be submitted via this form by 11:59 pm.
  • Fri, Feb 4: Advisors let students know whether they can continue with the plan in the abstract or whether more discussion is needed.
  • Fri, Mar 11: Each student will create an electronic poster and submit a 4-minute zoom recording to present the poster, along with a link to their capstone github. The zoom links will be shared with other students immediately (see the next bullet item).
  • Wed, Mar 16: Students will be assigned to view and provide written feedback on a subset of other students' presentations. Students will be evaluated on the thoughtfulness of the comments they provide to others. Feedback will be due by 11:59 pm on Mar 16, before spring break begins. Instructions will be provided.
  • After the break: Each student will receive feedback from an advisor, along with the peer comments. The feedback will include an indication that the student is well on track to complete the capstone or needs substantial additional work.
  • Thu, Apr 21, 12:45-2pm: Save the date! In-person poster session where students will present final printed posters. Students will submit final electronic materials before the poster session. All data science majors (not just those completing capstones) will be encouraged to attend the poster event.
  • Each student will be notified as to whether they have passed the capstone requirement.