Skip to content

README.md

Latest commit

 

History

History
56 lines (42 loc) · 2.71 KB

README.md

File metadata and controls

56 lines (42 loc) · 2.71 KB
Raw
Typing SVG

Python FastAPI HTML5 CSS3 JavaScript

🏦 Finexcore: AI Lending Intelligence

An enterprise-grade, explainable AI (XAI) dashboard for deep credit risk assessment. It features a hyper-modern, deep slate dashboard with high-visibility neon accents, processing both individual applications and batch CSV portfolio scoring.

Dashboard Preview

✨ Key Features

  • ⚡ Real-Time Scoring Engine: Instantly compute default probabilities using an active ML backend.
  • 📈 Portfolio Batch Processing: Drag-and-drop CSV upload for scoring entire loan portfolios with aggregated KPIs.
  • 🔍 Full Explainability (XAI): Built-in SHAP feature-importance visualizations detailing exactly why a decision was made.
  • 🎨 Premium Dark Dashboard: A meticulously crafted, completely local UI featuring glassmorphism, responsive grids, and fluid tab navigation.
  • 📊 Interactive Analytics: Powered by Chart.js tailored for optimal dark-mode viewing.

🚀 Quick Start

1. Launch the AI Backend

The ML engine relies on Python APIs returning SHAP arrays and tier decisions.

cd backend
pip install -r requirements.txt
python main.py
# Server will default to localhost:7860

2. Open the Interface

The application requires absolutely no build step. Simply open the index.html file in your favorite web browser!

start index.html # On Windows
open index.html  # On Mac

🛠️ Architecture

  • Frontend: Pure HTML5/CSS3/Vanilla JS (Single-File App), Chart.js via CDN.
  • Backend Architecture: Python API endpoints (/predict, /predict/csv, /model/info).
  • Design Tokens: Deep slate #09090b heavily accented with vivid neon lime #a3e635.

📜 Notice

This dashboard was built as part of the Finexcore AI Risk Infrastructure.