Course Syllabus
Complete course overview, policies, and schedule
Course Information
Course Title
Data 198: Fashion x Data Science
Course Number
Data 198
Semester
UC Berkeley, Spring 2026
Lead Facilitator
Janhavi Revashetti
Email: jrevashe@berkeley.edu
Office Hours
N/A
Class Schedule
Mondays, 6:30 - 8 pm
Dwinelle 223
Course Description and Learning Objectives
Fashion x Data Science is a DeCal course designed to introduce how data science concepts are used within the fashion industry by balancing technical skills with practical applications. Topics will build upon each other every week along with small focused projects. Students will form teams to complete a capstone project as the final assessment. The top three projects will be chosen to present to a panel of industry experts and may receive the opportunity for external collaboration.
By the end of the semester students will be able to:
- •Analyze how and why data science is relevant across various fashion sectors
- •Apply statistical analysis and machine learning techniques to find insights from fashion datasets
- •Build predictive models for sales forecasting, A/B testing and trend forecasting using fashion datasets
- •Use computer vision and natural language processing methods for classifying fashion products and performing sentiment analysis
- •Evaluate sustainability benefits in circular fashion solutions
- •Present weekly project findings through detailed reports and a final capstone project
Course Impact
The goal of this course is to demonstrate the overlap that objective fields like data science can have with creative industries by not only teaching the necessary technical skills but also providing the opportunity to make a real-world impact through potential industry collaborations. The intersection of fashion and technology is rapidly evolving but is uncommon to encounter in academic settings. Therefore, this course would position Berkeley as one of the few universities exploring this interdisciplinary field through a data-driven perspective.
Prerequisites
Basic python fundamentals are helpful, however, this course is designed to also work for those with zero to no prior programming experience. It is aiming to teach technical concepts under the lens of the fashion industry.
Grading Breakdown
+ Bonus Extra Credit for winning final project pitches
Final Project Details
Students will complete a semester-long capstone project and will present findings to industry guests/peers. While students are encouraged to begin brainstorming and informally iterate on potential ideas at any point in the semester, formal project work will begin in the second half of the course, approximately six weeks in, after key foundational skills have been introduced.
The capstone is the primary requirement to pass this course and is expected to involve about 4–5 hours of independent or group work per week starting from the 6th week, in addition to class meetings. Students may either select a project from a database of provided ideas (currently in development) or propose their own.
Course staff will regularly meet with students to ensure final projects are on par with expectations and are compelling to present to industry leaders. Evaluation will be based on three components: the initial proposal (10%), which focuses on implementation planning and serves as an opportunity for written feedback from course staff; the creativity and potential impact of the final idea or project (20%); and the quality of the final pitch presentation (20%). Extra credit will be given to the winning groups.
Attendance
In order to pass this course, each lecture must be attended (with a maximum of two absences).
Late Policy
Each weekly assignment must be completed (with a max of one drop and 4 total slip days over the semester). Weekly assignments will be graded on accuracy + effort. We are trying to award grades based on how well students have understood the content/technical skills to finish the project. Honest efforts (with some inaccuracy) can still get full credit, however, assignments with little to no effort shown to understand course content will get 0%.
Grading Feedback
Students will receive timely grading on weekly assignments from course staff via Gradescope. The staff aims to return grades within 10 days of the assignment due date. Feedback will mainly be given for the final project. If students want personal feedback, they will be directed to visit one of the course-facilitators during office hours.
Pre-, Mid-Semester and End-of-Semester Surveys will be posted for students to give feedback on the instructors, course materials, etc. Questions found on https://teaching.berkeley.edu/resources/course-evaluations-question-bank will be used for the surveys.
Methods of Instruction/Resources
Weekly in-person lectures will require attendance for students. Lecture will include going over coding labs to make it easier for students to complete weekly assignments/capstone projects.
Weekly readings will be assigned as a supplement to lecture in additional external course resources.
Weekly projects and the final capstone project will be ways students demonstrate their learning.
Materials
Installation of Jupyter notebook or preferred IDE environment. This course will be taught in Python.