CSILoanPredictionModel

Loan Approval Prediction System using Streamlit & Machine Learning

This project is an interactive web application built using Streamlit that predicts whether a loan application will be approved or not based on user-provided financial and personal details.

It uses a pre-trained machine learning model (loan_approval_model.pkl) and a scaler (loan_approval_scaler.pkl) to process and predict outcomes in real time.

---

Features

• Predicts loan approval status using a pre-trained ML model
• Interactive user interface built with Streamlit
• Real-time input scaling and encoding using scikit-learn
• Uses LabelEncoder and StandardScaler for preprocessing
• Customized sidebar with contact and project details

---

Project Structure

LoanApprovalPrediction/
│
├── loan_approval_model.pkl          # Trained ML model
├── loan_approval_scaler.pkl         # StandardScaler used during training
├── app.py                           # Main Streamlit app code
├── requirements.txt                 # Dependencies
├── README.md                        # Project documentation
└── celebal label cover picture.png  # Sidebar image

---

Installation and Setup

Follow these steps to run the project locally:

Clone the Repository

git clone https://github.com/gschandrasekhar/LoanApprovalPrediction.git
cd LoanApprovalPrediction

Create a Virtual Environment (optional but recommended)

python -m venv venv
venv\Scripts\activate       # On Windows

Install Required Libraries

pip install -r requirements.txt

If you don’t have a requirements.txt, create one with:

pip install streamlit scikit-learn numpy joblib
pip freeze > requirements.txt

Run the Streamlit App

streamlit run app.py

---

How It Works

1. User Input:

   • The user enters details such as Age, Income, Employment Status, Loan Amount, and Loan Purpose.

2. Preprocessing:

   • Inputs are encoded and scaled using LabelEncoder and StandardScaler (same as used during training).

3. Prediction:

   • The trained ML model (loan_approval_model.pkl) predicts whether the loan will be approved.

4. Output:

   • The app displays one of the following messages:

     • ✅ "Yes!! you are eligible for the loan"
     • ❌ "No!! you are not eligible for the loan"

---

Tech Stack

Category	Tools / Libraries
Language	Python
Frontend / UI	Streamlit
Machine Learning	scikit-learn
Data Handling	NumPy, Pandas
Model Persistence	Joblib
Scaler / Encoder	StandardScaler, LabelEncoder

---

UI Overview

• Sidebar: Displays developer info, contact links, and technologies used.
• Main Section: Contains user input fields, prediction button, and result display.

---

Future Improvements

• Add more real-world financial features (credit score, loan history, etc.)
• Integrate a database to log user predictions
• Deploy on Streamlit Cloud / Hugging Face Spaces
• Add data visualizations for loan trends

---

👨‍💻 Author

Siva Chandra Sekhar Guttikonda 💼 LinkedIn 💻 GitHub 📧 Email

---

🪪 License

This project is licensed under the MIT License — feel free to use, modify, and distribute it for educational purposes.