Abstract

🚀 Machine Learning Project: Visa Approval Prediction

Introduction

This is machine learning project that predicts visa approval outcomes using applicant and job-related data.

The project involved:

• Data preprocessing and feature engineering
• Handling class imbalance using SMOTE
• Training multiple models (Logistic Regression, Random Forest, XGBoost)
• Evaluating models using accuracy, precision, recall, and F1-score

The goal was to identify key factors influencing visa approval decisions and build a predictive model.

Key technologies used:
Python, Pandas, Scikit-learn, XGBoost, Matplotlib, Seaborn

You can explore the full project here:
🔗 GitHub Repository: https://github.com/RamyaNandhan/machineLearning/tree/main/advanced_ml_project

#MachineLearning #DataScience #Python #AIProjects #LearningInPublic

Architecture

Conclusion

Machine Learning Models Tested

• Logistic Regression
• Random Forest
• XGBoost

The models were compared using accuracy, precision, recall, and F1 score to determine the best performer.

Future Improvements

• Deploy model using FastAPI
• Build a prediction web app
• Add automated ML pipeline
• Implement model explainability (SHAP)