Code Fashionably: Retail Machine Learning for Business

Name: Code Fashionably: Retail Machine Learning for Business
Rating: 5.0 (5 reviews)

Build product classification, demand forecasting and customer segmentation with real retail data. No heavy math required

Created byNneka Penniston

Last updated 2/2026

English

English [Auto],

What you'll learn

Build a product classification system using TF-IDF and Random Forest to automatically categorize thousands of products
Create demand forecasts using Prophet algorithm and evaluate forecast quality for inventory planning decisions
Develop customer segments using K-means clustering and RFM analysis to create actionable marketing strategies
Calculate business ROI and translate machine learning metrics into dollar impacts that stakeholders understand
Query and analyze large datasets using BigQuery and build models in Colab with free tools and no software installation

Course content

8 sections • 54 lectures • 2h 23m total length

Welcome & Course Overview0:54
Understand how this course is structured, what problems you’ll solve, and how retail data is used to build practical machine learning projects from start to finish.
Student Success Guide4:08
Learn how to pace the course, manage notebooks and datasets, and avoid common pitfalls so you can complete the projects efficiently as a busy professional.
Setup Part 1: Your Python Environment1:31
Set up Google Colab so you can run all course notebooks in the cloud and focus on learning, not local installations.
Setup Part 2 : BigQuery Access1:35
Set up BigQuery to access global datasets including retail.
Python Part 1: Hello World2:25
Python Refresher Course for Fashion Analytics
Python Part 2 : Variables2:47
Learn how to create Python variables for a fashion product, using strings, integers, floats, booleans, checking types, printing values, and computing the total cost.
Python Part 3: Lists3:13
Python Part 4: Dictionaries2:51
Python Part 5: Loops3:13
Learn how to use loops in Python to process each item in a list, iterate with for loops and range, and compute total inventory value by multiplying price and quantity.
Python Part 6: Conditionals2:53
Python Part 7: Functions2:05
Python Part 8: Pandas (CRITICAL)4:22
Python Part 9: Visualization1:46
Learn to visualize retail data with Python, pandas, and matplotlib, creating and sorting data frames by price and sales to generate bar charts that reveal key insights.
Python Part 10: Final Scenario1:36
Section 1 Checkpoint: Runway Ready?
Milestone: Cleared for the Runway0:08
Celebrate a milestone in retail machine learning for business as you prepare to take off and apply code-driven insights on the runway.

The CRISP-DM Framework2:29
Learn how to use the CRISP-DM lifecycle to structure machine learning projects, from defining business goals to deploying usable results.
The Five Challenges Framework1:53
Apply a practical checklist to identify common risks in ML projects, including data quality, alignment, and adoption, using fashion retail examples.
Translation Framework Workshop1:08
Practice turning vague business questions into clear ML problem statements, success metrics, and constraints you can actually model.
Industry Examples & Applications1:44
Explore real-world examples of machine learning in fashion and adjacent industries to see how these frameworks are applied in practice.
CRISP-DM and Business Translation
Milestone: Strategy Frameworks Mastered0:08
Master strategy frameworks for retail machine learning in business to reach this milestone. Apply these frameworks to optimize retail decisions using machine learning insights.

Business Case: Classification Problem2:02
Understand why manual product tagging doesn’t scale, what success looks like for automated classification, and how the business will use the results.
Classification Project Walkthrough8:16
Build a text classification model step by step using product titles and descriptions, and learn how each modeling choice affects results.
TF-IDF Deep Dive2:17
Learn how TF-IDF converts text into meaningful numerical features and why it helps models distinguish between product categories.
Evaluation Metrics for Classification1:48
Compare accuracy, precision, recall, and F1 score, and learn which metrics matter most for real-world classification decisions.
Classification Basics
Project Milestone Reached0:08
Great work finishing this project lab! I'll see you in the next section.

Business Case: Forecasting Problem1:47
Frame the demand forecasting challenge and understand how forecast accuracy impacts inventory planning, markdowns, and stockouts.
Time Series Primer1:33
Learn core time-series concepts like trend, seasonality, and train/test splits to prepare for building forecasting models.
Forecasting Project Walkthrough8:28
Build and interpret a demand forecasting model, including forecasts, uncertainty intervals, and business-facing outputs.
Evaluation Guide for Forecasting2:03
Learn how metrics like MAPE are used to evaluate forecasts and decide whether a model is good enough for business use.
Demand Forecasting
Project Milestone Reached0:08
Great work finishing this project lab! I'll see you in the next section.

Business Case: Segmentation Problem1:27
Understand why customer segmentation matters in fashion retail and how RFM analysis supports targeted marketing decisions.
Clustering Primer1:38
Learn the core idea behind clustering and how it’s used to group customers with similar purchasing behavior.
RFM Analysis Guide2:21
Learn how to calculate Recency, Frequency, and Monetary values from transaction data and prepare them for clustering.
Segmentation Project Walkthrough10:47
Run the RFM segmentation analysis, interpret clusters, and connect each segment to concrete marketing actions.
Segment Profiles Template4:05
Use a practical template to document segment definitions, recommended actions, and KPIs for business stakeholders.
RFM Segmentation
Project Milestone Reached0:08
Great work finishing this project lab! I'll see you in the next section.

Using Large Language Models in Fashion3:03
Explore how large language models can support product copy, analysis, and idea generation within fashion analytics workflows.
OpenAI API Setup Guide3:42
Set up a simple connection to the OpenAI API and learn how to integrate language models into analytics notebooks.
The AI Merchant4:44
Use GPT-4 and prompt engineering to analyze thousands of fashion reviews with a scalable sentiment analyzer, achieving rapid ROI (about 20 dollars per 1,000 reviews) beyond star ratings.
Lab Milestone: LLM Sentiment Analysis Complete0:08
Congratulations on completing the LLM Sentiment Analysis lab! You've now seen how to bridge the gap between structured machine learning and the power of language models.
Dashboard Setup for Analytics6:44
Learn how to design dashboards that communicate ML results clearly and help stakeholders make decisions.
Dashboard Milestone: Python and Tableau Dashboard Executive Dashboard0:08
Create executive dashboards using Python and Tableau to present retail machine learning insights for business decisions. Achieve dashboard milestones that convert data into actionable business intelligence.
A/B Testing Setup15:02
Learn how to design basic A/B tests to measure whether your models actually improve business outcomes.
Analytics Tools & Experiments
Milestone: Advanced Tools & Analytics Complete0:08
Complete the milestone of advanced tools and analytics for retail machine learning in business, and apply practical analytics techniques from the course Code Fashionably.

Ethics Checklist for ML in Fashion1:54
Apply a practical ethics checklist to evaluate data sources, modeling choices, and downstream business impact.
Ethical Web Scraping Guide2:06
Learn how to collect web data responsibly, legally, and ethically for analytics and ML projects.
Cross-Functional Collaboration1:53
Learn how to work effectively with merchandisers, marketers, and engineers so your models are understood and adopted.
Ethics & Collaboration
Milestone: Ethics & Collaboration Mastered0:08
Milestone: ethics and collaboration mastered in retail machine learning for business. Ethics and collaboration mastered in retail machine learning for business.

Portfolio Template & Guidance1:16
Learn how to package your projects into a clear portfolio that demonstrates business impact, not just code.
Executive Summary Template0:56
Practice writing concise executive summaries that communicate ML results to non-technical stakeholders.
Industry Adaptation Guide0:58
Learn how to adapt the techniques from this course to other industries beyond fashion.
Strategy Playbook3:14
See how classification, forecasting, and segmentation fit together into a broader analytics strategy.
Reading List & Congratulations0:32
Get curated resources to continue building your skills in machine learning, analytics, and retail strategy.
Master Quiz
Bonus Lecture5:22

Requirements

Basic Python skills - able to read pandas dataframes and understand basic syntax
Understanding of basic statistics like mean, median, standard deviation, and correlation
Google account for BigQuery and Colab (both free, no credit card required)
No machine learning experience required - we explain concepts visually and intuitively

Description

Learn machine learning by building real projects with retail data. This course focuses on understanding ML concepts, building models, and calculating business impact. We don't cover deployment or production systems. Instead, you'll master the skills that come first: knowing which models to build, how to evaluate them, and how to prove they're worth building.

This course is designed for business analysts, product managers, and career changers who already have a basic grasp of Python. To ensure you are ready for the projects, we start with "Getting Runway Ready" (a specialized onboarding section that includes a 10-part Python Refresher series). These bite-sized videos bridge the gap between general Python knowledge and the specific data manipulation skills required for high-level retail analytics.

You'll work with real transaction and product data from Google BigQuery's public "TheLook" ecommerce dataset. You will learn how to access this global data warehouse directly. This is a professional skill that allows you to find and query data in any industry.

I chose retail and fashion data for three reasons: the problems are universal, the data is visual, and the business impact is easy to calculate. Once you understand how ML solves retail problems, you can adapt these techniques to any domain, including healthcare or finance.

You'll build three complete machine learning projects:

Product Classification: Automatically categorize thousands of products using classification algorithms.
Demand Forecasting: Use the Prophet library to predict sales trends and prevent stockouts.
Customer Segmentation: Use K-means clustering and RFM analysis to personalize marketing.

Each project walks you through the complete process: understanding the business problem, preparing data, building the model, and calculating the dollar value of your work.

All tools are free. You’ll use Google BigQuery to access "The Look" public dataset and Google Colab to run your code in the browser. I provide curated datasets and complete Python notebooks for every project so you can focus on the analysis, not the data cleaning.

Each project includes professional documentation templates (executive summaries and ROI calculators) giving you three complete case studies for your professional portfolio.

This course is not for complete programming beginners. It is for those who know the basics of Python and want to apply those skills to solve real-world business problems with Machine Learning.

This course is created and taught independently by Nneka J. Penniston. While the instructor teaches as Adjunct Faculty at Columbia University, this course is not affiliated with, endorsed by, or sponsored by Columbia University or NYU Stern School of Business.

Who this course is for:

Business analysts and analytics professionals who want to add machine learning to their skillset and build their first ML portfolio
Product managers who need to understand ML capabilities and evaluate ML opportunities for their products
Career changers with basic Python knowledge who want to apply ML to solve real business problems
Anyone in retail, ecommerce, or any industry who wants to use data to solve business problems with machine learning

Code Fashionably: Retail Machine Learning for Business

What you'll learn

Explore related topics

Course content

Introduction: Getting Runway Ready15 lectures • 35min

Module 1: ML Foundation & Business Framework5 lectures • 7min

Project 1: Product Classification5 lectures • 15min

Project 2: Demand Forecasting5 lectures • 14min

Project 3: Customer Segmentation6 lectures • 20min

Advanced Topics & Modern Tools8 lectures • 34min

Ethics & Professional Practice4 lectures • 6min

Building Your Career & Next Steps6 lectures • 12min

Requirements

Description

Who this course is for: