Fall 2021 EECS 498-014
Data Science Projects
This course will provide opportunities for students to apply advanced data science techniques to real-world problems. Students will work in a team throughout the semester on a project as part of a collaboration between the Michigan Institute for Data Science (MIDAS) and its Industry Partner Yazaki.
Throughout the course, students will apply various supervised and unsupervised machine learning techniques, with the ultimate goal of optimizing the engineering specifications used to ensure the safety and reliability of electrical connections within the automotive industry.
4 credit hours. This course is an approved Data Science Capstone for undergraduates in the Data Science-Engineering program.
Students must have received credit for either EECS 445 – Introduction to Machine Learning or EECS 476 – Data Mining, or their equivalent. Students should be comfortable in coding in either Python or MATLAB.
None. Slides and other course materials will be distributed through Canvas.
- Formulate and execute a research plan for applying data science to a real-world dataset.
- Understand the issues of applying data science techniques to real-world datasets and how to mitigate them.
- Communicate research results with both domain experts and a general audience.
All meetings will be held in Room 2238 CSRB from 1:30-3:00 PM unless otherwise noted.
- Thursday, September 2 – Course Introduction, Research Plans, and Introduction to Research Projects
- Tuesday, September 7 – Kickoff meeting with Industry Partner staff (Zoom)
- Thursday, September 9 - Project Discussion and Overview of Relevant Data Science Techniques
- Wednesday, September 15 - Draft Research Plans due at 4 PM
- Thursday, September 16 - Review of Research Plans
- Wednesday, September 22 - Revised Research Plans due at 4 PM
- Wednesday, September 29 and every Wednesday until December 1 - Meeting Agendas due at 4 PM
- Thursday, September 30 and every Thursday until December 2 – Weekly Progress Meeting - Summaries due by 4 PM Friday
- Friday, October 15 – Meeting with Industry Partner staff (Zoom)
- Friday, October 22 – Midterm reports due at 4 PM
- Tuesday, November 16 – Meet with Industry Partner staff (Zoom)
- Friday, December 10 – Final reports and project deliverables due at 4 PM
- Tuesday, December 14 – Final presentations
Holiday/Study Breaks (No Meetings):
- October 19 - Study Break
- November 25 – Thanksgiving Recess
10% Participation in Weekly Meetings, 10% Participation in Monthly Meetings with Industry Partner staff, 30% Midterm Report, 40% Final Report and Project Deliverables, and 10% Final Presentation.
- Weekly Meetings – Every week all students will participate in an hour-long progress meeting. Each team will be required to set a meeting agenda in advance for their team’s discussion. Each team will produce a weekly summary of the meeting that will include a description of each team member’s activities, meeting minutes, intermediary results, and action items for the following week. Team members will rotate the responsibility of setting the agenda and leading their team’s discussion.
- Monthly Meetings - Each student team will meet individually for a one-hour virtual monthly meeting with Industry Partner staff. During this meeting, students will provide a short presentation of the current status of the project, from which Industry Partner staff will have the opportunity to ask questions of and provide feedback to the students.
- Midterm Report - Each team will be required to submit for evaluation a mid-term progress report. The progress report must detail a) the data science methods chosen and their scientific rationale, b) steps taken to address the research question, with both positive and negative findings, c) the current state of their proposed solution, d) a timeline outlining their remaining work, and e) anticipated challenges and how to address them.
- Final Report and Project Deliverables - Each team will be required to submit for evaluation a final progress report. The final report must detail a) positive and negative findings, b) the final results of their proposed solution, c) how the proposed solution meets the stated Industry Partner goals of the project, and d) how the solution fits into the overall Industry Partner goal of applying data science to their business/industry. Students will also be required to submit project deliverables, e.g., a database or trained machine learning model, along with the final report.
- Final Presentation – Each team will prepare a presentation for an end of semester event that will be held virtually and attended by Industry Partner staff and MIDAS affiliated faculty and students. Industry Partner staff will have the opportunity to provide public feedback to the participating teams during this event.
- Attendance – All team members are expected to attend all requisite meetings throughout the semester. In the case of scheduled absences, the instructor must be notified in advance.
- Academic Integrity – Students will perform their work in accordance with their schools’ respective academic integrity or honor code policies (e.g., LSA, College of Engineering)
- Late Assignments – Late assignments will not be accepted without prior written consent by the instructor.
Please note that given the ongoing COVID-19 pandemic it is understood that students may be face additional challenges in completing their coursework. Please notify the instructor of your needs and reasonable accommodations will be made for these policies.
- Accommodations – Please notify the instructor directly prior to the start of the course of any existing accommodations. New accommodations should be submitted through the Services for Students with Disabilities
- Mental Health Resources - Please refer to the Resources for Stress and Mental Health website for a listing of resources for students.
- Information Technology – Please refer to the Information and Technology Services website for various IT needs, including their Remote Resource Guide for remote learning and study.
The syllabus page shows a table-oriented view of the course schedule, and the basics of course grading. You can add any other comments, notes, or thoughts you have about the course structure, course policies or anything else.
To add some comments, click the "Edit" link at the top.