Schedule & Assignments

Weekly schedule with topics, assignments, and due dates

Week 1: Fashion Industry Basics and Data Literacy

Overview: Explore data science applications across the fashion industry and understand the business impact

Topics: Introduce different fashion sectors and their respective business models, data sources in the industry, how data is used from a business perspective in the various fashion sectors

Assignment: Create a report for a select fashion brand and identify how/why data is applied and the respective business impact

Week 2: Intro to Python

Overview: Python Fundamentals

Topics: Data Types, Variables, Basic Operations, Lists, Dictionaries, Loops, Writing Basic Functions

Assignment: Create a basic financial calculator that determines the revenue, costs, and profits for the sales of summer clothes inE-commerce Wish Dataset (or any other publicly available data set of choice). Generate a report that describes what was done, methods used, the findings/implications, and any limitations.

Week 3: Data Collection Methods

Overview: Learn how data is collected and used in the fashion industry

Topics: Web scraping fundamentals and ethics, APIs and data partnerships, Data collection design, Data quality frameworks used in the industry

Assignment: Design a data collection framework for a real or hypothetical fashion-tech startup. Must include ethical boundaries and technical concepts used.

Week 4: Exploratory Data Analysis

Overview: Use exploratory data analysis to find patterns in fashion datasets

Topics: Data Cleaning, Descriptive Statistics, Visualization Practices

Assignment: Using theFashion Retail Sales dataset, explore any relationship between products sold and the corresponding price. Generate a report that describes the purpose, methods used, the findings/implications, and any limitations.

Week 5: Data Analytics and Segmentation

Overview: Use statistical techniques and clustering to understand consumer behavior

Topics: Feature Engineering, Clustering Algorithms (K-Means, Hierarchical, PCA)

Assignment: Using theAdidas vs Nike dataset perform an analysis comparing the two brands using this week's (and/or previous week's) topics. Generate a report that describes what was done, methods used, the findings/implications, and any limitations.

Week 6: A/B Testing and Experimentation

Overview: Design and interpret experiments for informed fashion business decisions

Topics: Experimental design in fashion context, Sample size calculations and power analysis, A/B testing platforms and tooling, Statistical significance

Assignment: Design and simulate a hypothetical A/B test using theH&M Personalized Fashion Recommendations dataset and accurately analyze the results. Generate a report covering the background, significance, hypothesis, methods to artificially generate results, analysis, and limitations (due to the artificial simulation).

Week 7: Predictive Modeling

Overview: Apply predictive modeling techniques for informed fashion business decisions

Topics: Time series analysis, regression models, classification models

Assignment: Predict the number of sales for a particular product and compare it to the actual number of sales using theOnline Retail Data Set. Generate a report covering the background, methods, analysis, and limitations (due to the artificial simulation).

Week 8: Computer Vision

Overview: Use computer vision techniques to analyze and classify fashion products

Topics: Pre-trained models and transfer learning, basic image classification and segmentation for products, Object detection, Feature extraction, Integration challenges

Assignment: Using a pre-trained model andFashion MNIST dataset, create a model that automatically classifies images to a product category. Generate a report covering the background, methods, analysis, and limitations (due to the artificial simulation).

Week 9: Natural Language Processing

Overview: Extract insights from large text databases to understand customer behavior and trends

Topics: Text preprocessing, Sentiment analysis for product review and social media, Topic modeling for trend identification, Brand monitoring and reputation management

Assignment: Perform sentiment analysis for a brand's product reviews using theAmazon reviews on Women dresses dataset. Generate a report covering the background, methods, analysis, and limitations (due to the artificial simulation).

Week 10: Circular Fashion

Overview: Data science applications within circular fashion

Topics: Resale optimization, impact measurement of circular fashion initiatives, consumer behavior and sustainable fashion

Assignment: Build a case study on the impacts of a circular fashion business model for sustainability impacts. Use topics from previous weeks to generate a data driven report

Week 11: Capstone Project Development Week

Overview: Hands-on development week for final project with opportunity for assistance from course staff

Week 12: Final Project Pitch and Industry Panel

Overview: Student presentations to class. Top 3 projects will be selected to present to a panel of experts working in this industry.

Topics: Topics of discussion include current biggest data challenges in fashion, emerging technologies and impacts on business metrics, various career pathways, skill gaps in current job market, future directions of fashion tech

Potential Speakers/Judges:

  • • Fashion Tech Startup Founder(s)
  • • Data Science Lead from Traditional Fashion Brand
  • • ML Engineer from Fashion E-commerce
  • • Fashion-Tech VC/Investor
  • • Fashion-Tech Product Manager
  • • Fashion-Tech Editor/Journalist

Assignment Guidelines

Report Requirements

  • • All reports should be data-driven and analytical
  • • Include clear methodology sections
  • • Discuss findings, implications, and limitations
  • • Use proper Python documentation and comments
  • • Submit both code and written report

Submission Policy

  • • Maximum of one assignment drop allowed
  • • 4 total slip days over the semester
  • • Graded on accuracy and effort
  • • Honest efforts with inaccuracies receive full credit
  • • No effort assignments receive 0%