NeuroCred

NeuroCred is a comprehensive full stack fintech platform that empowers users with AI-driven financial insights and decision making tools. The platform leverages advanced machine learning models to provide loan approval predictions, CIBIL score calculations, and intelligent financial guidance through an AI chatbot.

Features

1. Loan Approval Prediction

• Predicts the chances of loan approval based on user inputs
• Provides SHAP-based explainability for influencing factors
• Generates human understandable insights

2. CIBIL Score Calculation

• Calculates an estimated CIBIL score based on key credit factors
• Provides a breakdown of score components
• Offers AI generated improvement suggestions

3. Loans & Finance Chatbot

• Answers finance and loan related queries
• Uses Chroma vector database for retrieving relevant information

4. MLOps and Tracking

• Uses MLflow for experiment tracking and DVC for data versioning

5. Authentication & Security

• JWT (JSON Web Token) based authentication system

Tech Stack

• Frontend: Next, Framer Motion and Tailwind CSS
• Backend: FastAPI
• AI/ML: XGboost, SHAP and LangChain
• MLOps: MLflow and DVC
• Database: Mongo and Chroma

Setup

Backend

1. Clone the repository:

   git clone https://github.com/Armaan457/NeuroCred

2. Navigate to the Backend directory:

   cd Backend

3. Create and activate a virtual environment:

   • macOS/Linux:

     python -m venv env
     source env/bin/activate

   • Windows:

     python -m venv env
     env\Scripts\activate

4. Install dependencies:

   pip install -r requirements.txt

5. Run the server:

   python main.py

Frontend

1. Navigate to the Frontend directory:

   cd Frontend

2. Install dependencies

   npm install

3. Start development server

   npm run dev

Developers

• Armaan Jagirdar
• Khusham Bansal