md-aseem / visa-approval-prediction-model

In this repository, I am predicting the probability of US student visa approval of students based on several features like university admitted, its rank, scholarship received etc.

Student Visa Approval Prediction

Project Overview

This project aims to predict the probability of student visa approval based on their credentials. Utilizing data collected from students' Facebook posts about their visa interview experiences, the project employs a neural network to make predictions. The model, which is an MLP (Multi-Layer Perceptron), achieves an 85% accuracy rate on the validation set.

Table of Contents

• Installation
• Methodology
• Results
• Contributing
• License
• Contact

Installation

To set up the project, follow these steps:

1. Clone the Repository

   git clone https://github.com/md-aseem/visa-approval-prediction.git
   cd visa-approval-prediction

2. Install Dependencies

   • Ensure Python 3.10 is installed.
   • Install required Python packages:

     pip install -r requirements.txt

Methodology

1. Data Collection: Scraping students’ Facebook posts using Python and structuring data with the ChatGPT API.
2. Data Analysis: Analyzing the data using seaborn for insights.
3. Data Modeling: Implementing and iterating over neural networks and decision trees; choosing MLP based on F-1 score.
4. Model Deployment: The model is deployed using Gradio and hosted on Google Cloud Run.

Results

The deployed model can be accessed at muhammadaseem.com/visaprobability. Over 1000 students have used this service, with feedback indicating its utility in improving visa approval chances.

License

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

Contact

Muhammad Aseem - [e-mail]

Project Link: https://github.com/md-aseem/visa-approval-prediction-model

---