This is a submission for the Bright Data Web Scraping Challenge: Most Creative Use of Web Data for AI Models
What I Built
Estile is an AI-powered fashion recommendation app designed to help users discover clothing articles tailored to their preferences. The app combines artificial intelligence and web scraping technologies to recommend outfits and automatically search for matching products on eBay in real time.
The app’s AI system suggests styles based on user preferences and trends. It then uses a custom fine-tuning process to optimize search keywords and ensure accurate product matching with items available on eBay.
Links
Frontend Code Repository
Backend Code Repository
Screenshots
How I Used Bright Data
Bright Data was instrumental in building Estile by enabling real-time data scraping and fine-tuning the AI model. Here’s how I leveraged it:
Real-Time Scraping for Clothing Recommendations - Using Bright Data’s Scraping Browser, I extracted data from dynamic and JavaScript-heavy websites to fetch the latest fashion items and trends. This ensured that recommendations were always fresh and relevant.
eBay Data Collection and AI Fine-Tuning - I utilized Bright Data’s Web Scraper API to collect and structure data from eBay. The data was used to train and fine-tune a language model (LLM) that matches AI-generated fashion descriptions with optimal product keywords. This allows the app to enhance search accuracy and deliver precise product suggestions to users.
Additional Prompt Qualifications
- Prompt 2: Build a Web Scraper API to Solve Business Problems – Estile demonstrates a practical use of web scraping to tackle challenges in product discovery and recommendation systems.
A big thank you as well to the DEV.to team for hosting this exciting hackathon. Also thank you for considering my project for the Bright Data Web Scraping Challenge!
Top comments (0)