Skip to content

README.md

Latest commit

 

History

History
192 lines (137 loc) · 5.81 KB

README.md

File metadata and controls

192 lines (137 loc) · 5.81 KB
Raw

🧠 DropAnalyze: AI-Powered E-Commerce Intelligence Platform

Status Python React AI License

Transforming Data into Dropshipping Profit with Generative AI & Computer Vision.

View Demo • System Architecture • Algorithms • Installation

⚡ Overview

DropAnalyze is a next-generation SaaS platform that automates the entire product research workflow for e-commerce entrepreneurs. Unlike basic scrapers, it uses a Hybrid Intelligence Engine combining:

  1. Headless Browsing (Playwright) for dynamic data extraction.
  2. Computer Vision for product image recognition.
  3. Large Language Models (LLM) for market strategy generation.

📸 Demo

Demo.mp4

Real-time analysis of market trends, competitor SEO, and AI-driven marketing strategies.

🏗 System Architecture

DropAnalyze utilizes a decoupled Client-Server Architecture. The flow of data from the raw URL to the final AI Insight is visualized below:

graph TD
    A[User Input URL] -->|REST API| B(FastAPI Backend)
    B -->|Spawns| C{Scraping Engine}
    C -->|Playwright| D[Headless Browser]
    D -->|Render & Extract| E[DOM & Image Data]
    E --> F{Analysis Core}
    F -->|Regex Heuristics| G[Price Normalizer]
    F -->|SEO Algorithm| H[Audit Scoring System]
    F --> I{AI Pipeline Gemini 2.5}
    I -->|Prompt Engineering| J[Marketing Strategy]
    I -->|Sourcing Logic| K[Supplier Finder]
    J & K & H --> L[JSON Response]
    L -->|State Update| M[React Frontend]
Loading

🧮 Core Algorithms

1. The "Inspector" Audit Algorithm (Weighted Scoring)

The competitor listing quality is evaluated using a proprietary weighted formula based on 4 key metrics:

$$ Score = \sum (w_{title} \cdot S_{seo}) + (w_{img} \cdot S_{res}) + (w_{price} \cdot S_{psych}) + (w_{desc} \cdot S_{density}) $$

Where:

  • Title Optimization: Checks for keyword stuffing vs. optimal length (10-200 chars).
  • Visual Quality: Detects placeholder images vs. high-res product shots.
  • Pricing Psychology: Analyzes price endings (.99, .90) for conversion optimization.
  • Content Density: Measures description verbosity.

2. AI Sourcing Logic

The system does not just search; it infers.

  1. Extraction: Extracts the "core product essence" from a localized retail title (e.g., "Trendyol Şarj Aleti").
  2. Translation & Standardization: Converts it to global manufacturing terms (e.g., "25W PD USB-C Adapter").
  3. Query Construction: Generates optimized search queries for Alibaba and AliExpress APIs.

✨ Key Features

Feature Technology Description
🕵️‍♂️ Sourcing Agent Gemini AI + Search API Reverse-engineers retail products to find original Chinese factories.
📊 Smart Audit Python + BeautifulSoup Grades competitor listings out of 100 based on SEO best practices.
🤖 Marketing Studio Generative AI Writes viral TikTok hooks, cold emails, and Instagram captions instantly.
📈 Trend Radar PyTrends + Recharts Visualizes search volume interest over time and potential risks.
🌍 Currency Sim React State Real-time profit calculation switching between USD, EUR, and TRY.
📄 Auto-Reporting JSPDF Generates professional PDF reports for agency clients.

📂 Project Structure

DropAnalyze/
├── client/                 # React Frontend
│   ├── src/
│   │   ├── components/     # Recharts & UI Components
│   │   ├── App.js          # Main Logic & State Management
│   │   └── App.css         # Glassmorphism Styles
├── server/                 # Python Backend
│   ├── main.py             # FastAPI Routes & AI Logic
│   ├── dropanalyze.db      # SQLite Portfolio Database
│   └── requirements.txt    # Python Dependencies
└── README.md               # Documentation

🚀 Installation & Setup

Prerequisites

  • Python 3.10+
  • Node.js 16+
  • Google Gemini API Key

1. Clone Repository

git clone https://github.com/komutan234/DropAnalyze-AI/tree/main
cd DropAnalyze

2. Backend Setup

cd server
python -m venv venv

# Windows:
.\venv\Scripts\activate

# Mac/Linux:
source venv/bin/activate

pip install -r requirements.txt
playwright install

3. Frontend Setup

cd client
npm install

4. Running the System

Terminal 1 (Backend):

cd server
python main.py

Terminal 2 (Frontend):

cd client
npm start

🤝 Contributing

Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

📝 License

Distributed under the MIT License. See LICENSE for more information.

Developed by Turgut Akin
Software Engineer & Full Stack Developer