This repository includes code for the paper "Towards Zero Touch Networks: Cross-Layer Automated Security Solutions for 6G Wireless Networks" published in IEEE TCOM, focusing on autonomous cybersecurity (physical-layer authentication and cross-layer intrusion detection) using AutoML techniques.

machine-learning data-stream feature-selection cybersecurity hyperparameter-optimization intrusion-detection adaptive-learning drift online-learning streaming-data concept-drift automl intrusion-detection-system 6g drift-detection physical-layer-security model-optimization cicids2017 physical-layer-authentication data-balancing

• Updated Mar 5, 2025
• Jupyter Notebook

a machine learning pipeline to predict heart disease risk based on demographic, lifestyle, and clinical features train advanced and predictive ml models

encoding machine-learning gui exploratory-data-analysis data-visualization artificial-intelligence data-analysis scaling data-preprocessing model-evaluation model-deployment model-training correlation-analysis classification-models streamlit data-balancing

• Updated Jan 12, 2026
• Jupyter Notebook

GAN-based credit card fraud balancing pipeline using TensorFlow/Keras to generate synthetic fraud transactions with preprocessing, PCA visualization, and distribution analysis.

python machine-learning deep-learning tensorflow scikit-learn keras gan pca imbalanced-data fraud-detection synthetic-data credit-card-fraud-detection generative-ai data-balancing

• Updated Apr 27, 2026
• Jupyter Notebook

Employee attrition prediction for an IT services company (1,470 employees, 3 HR sources). Domain-driven feature engineering, Dummy / logistic regression / XGBoost comparison, decision threshold tuned on F2-score, global and local interpretability with SHAP.

scikit-learn xgboost classification logistic-regression feature-engineering feature-importance shap onehot-encoding shapley-values xgboost-classifier data-balancing threshold-optimization

• Updated Nov 10, 2026
• Jupyter Notebook

This project presents a complete, end-to-end fraud detection system designed to identify fraudulent financial transactions in real-time while minimizing customer friction. The solution goes beyond model building to address deployment strategy, threshold optimization, explainability, and production monitoring considerations.

logistic-regression feature-engineering xgboost-classifier data-balancing

• Updated Jan 13, 2026
• Jupyter Notebook

Machine learning-based prediction of customer churn in the telecom industry using data balancing and ensemble models.

machine-learning prediction telecom classification ensemble-models customer-churn data-balancing

• Updated Sep 18, 2025
• Jupyter Notebook

A credit risk prediction project for LoanTap using machine learning to classify loan repayment behavior. It focuses on data preprocessing, handling imbalance, and optimizing model performance for real-world lending decisions.

visualization eda recall logistic-regression precision smote f1-score data-balancing

• Updated Jun 18, 2025
• Jupyter Notebook

Parkinson's Disease Prediction using Machine Learning with a web-based interface built with React, Flask, and Node.js for real-time predictions and user history tracking.

nodejs machine-learning mongodb reactjs expressjs feature-selection jwt-authentication flask-api ensemble-machine-learning tailwindcss data-split auc-roc react-hot-toast lucide-react data-balancing

• Updated Apr 17, 2025
• Jupyter Notebook