📚 Machine Learning Projects

📌 Overview

This repository contains a collection of machine learning projects completed during the Fundamentals of Machine Learning and Advanced Methods in Data Science courses at the German University in Cairo (GUC). The projects cover both clustering and classification domains and leverage real-world and synthetic datasets to demonstrate a wide range of machine learning techniques and evaluation strategies.

---

📁 Repository Structure

Machine_learning/
├── Clustering_projects/
│   ├── Iris_clustering_project.ipynb
│   ├── Moons_clustering_project.ipynb
│   ├── data/
│   └── README.md
│
├── Classification_projects/
│   └── Detecting Cyber Security Threats using Deep Learning/
│       └── notebook.ipynb + data
│
│   └── Indian Telecom Customer Churn Prediction/
│       └── notebook.ipynb + data
│
│   └── Predict the presence of heart disease/
│       └── notebook.ipynb + data
│
│   └── README.md
│
│
└── README.md

---

🔍 Project Summaries

1️⃣ Clustering Projects Clustering Projects

🌸 Iris Clustering

• Objective: Group different iris species using unsupervised learning.
• Techniques: K-Means, Hierarchical Clustering, DBSCAN.
• Evaluation Metrics: Silhouette Score, Inertia.

🌙 Moons Dataset Clustering

• Objective: Evaluate clustering methods on a synthetic, non-linear dataset.
• Techniques: K-Means, Hierarchical Clustering, DBSCAN.
• Evaluation Metrics: Cluster shape visualizations, Silhouette Score.

---

2️⃣ Classification Projects Classification_projects

🛡️ Detecting Cyber Security Threats using Deep Learning

• Objective: Classify malicious vs. benign network events using PyTorch.
• Techniques: FeedForward Neural Network(FFNN) with Dropout, Early Stopping, Imbalanced Data Handling.
• Evaluation: Accuracy, Precision, Recall, F1-score, Confusion Matrix, ROC Curve, PR Curve.

📞 Indian Telecom Customer Churn Prediction

• Objective: Predict customer churn using usage patterns and demographic data.
• Techniques: Logistic Regression, Random Forest, SVM + SMOTE.
• Evaluation: F1-Score (especially on minority churn class), Precision, Recall, Confusion Matrix.

❤️ Predicting Heart Disease

• Objective: Predict the presence of heart disease based on clinical parameters.
• Techniques: K-Nearest Neighbors, Logistic Regression, Decision Trees.
• Evaluation: Accuracy, Precision, Recall, F1-score, Confusion Matrix, ROC Curve.

📄 For more detailed project-level documentation, see the README in each subfolder:

• Clustering Projects
• Classification Projects

---

🛠 Technologies Used

• Language: Python
• Tools & Libraries:
  • pandas, numpy, matplotlib, seaborn
  • scikit-learn, PyTorch (for DL project)
• Environment: Jupyter Notebook

---

🚀 How to Run the Projects

1. Clone the repository

   git clone https://github.com/Ajeeb-Alameen/Machine_learning.git
   cd Machine_learning

2. Navigate to a project and open the notebook

   cd Clustering_projects  # or Classification_projects
   jupyter notebook <notebook_name>.ipynb

---

📈 Project Flow

Each notebook typically includes:

• Exploratory Data Analysis (EDA)
• Model Building & Evaluation
• Performance Metrics & Visualizations
• Final Discussion & Insights

---

✅ Next Steps

• Apply hyperparameter tuning and cross-validation
• Explore ensemble and boosting methods (e.g., XGBoost, LightGBM)
• Expand datasets and incorporate feature selection
• Improve generalization using regularization techniques

---

🔗 Links

• 📂 GitHub Repository: Machine Learning Repo
• ✍ Author: Ajeeb Alameen
• 📧 Email: ajeebizzalameen@gmail.com
• 🔗 LinkedIn: Ajeeb Alameen

---