DEV Community

Cover image for Estile: AI-Driven Clothing Recommendations Enhanced by Bright Data Scraping
Erick Christian
Erick Christian

Posted on

1 1 2 1

Estile: AI-Driven Clothing Recommendations Enhanced by Bright Data Scraping

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

Home

Loading

Result

Fine-tuning logging

Fine-tuning process

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:

  1. 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.

  2. 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!

Image of Docusign

Bring your solution into Docusign. Reach over 1.6M customers.

Docusign is now extensible. Overcome challenges with disconnected products and inaccessible data by bringing your solutions into Docusign and publishing to 1.6M customers in the App Center.

Learn more

Top comments (0)

The best way to debug slow web pages cover image

The best way to debug slow web pages

Tools like Page Speed Insights and Google Lighthouse are great for providing advice for front end performance issues. But what these tools can’t do, is evaluate performance across your entire stack of distributed services and applications.

Watch video