Code
Deep Learning for Sustainable Fashion Visual Search
Overview
What this challenge is about.
You are given a dataset of 10k product images (from a subset of the catalog) with metadata (category, price, material). Build a visual search pipeline: extract embeddings using a pre-trained CNN (e.g., ResNet50), index them with FAISS, and implement a query-by-image function. Evaluate retrieval quality using precision@k and recall@k. Deliver a working prototype (Python script or notebook) and a business case (2 pages) estimating impact on conversion rate and average order value. Constraints: use only open-source models; no fine-tuning; must run on a laptop.
The Brief
What you'll do, and what you'll demonstrate.
Prototype a visual search system to improve product discovery and conversion.
Earning criteria — what you'll demonstrate
- Apply deep learning to a real-world image retrieval task
- Use pre-trained CNNs for feature extraction
- Implement efficient similarity search with FAISS
- Quantify business value of a technical solution
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.