🧠 Depression Risk Prediction using Unsupervised Learning

Depression is a growing global health issue, and early identification of individuals at risk is crucial for effective intervention. This project explores depression risk prediction using unsupervised machine learning, focusing on K-Means clustering.

🔍 Project Objective

To identify clusters or patterns among individuals based on:

• Lifestyle and physical health
• Mental health history
• Social interactions and sleep habits

without relying on any predefined labels.

🧪 Methodology

• Data Preprocessing: Null handling, normalization, and encoding of categorical variables
• Clustering Algorithm: K-Means
• Evaluation:
  • Elbow Method for optimal k
  • PCA for 2D visualization of clusters
• Interpretation: Each cluster represents a group with distinct depression risk profiles

📊 Output

• Clusters visualized via PCA
• Insights into risk factors and mental health patterns
• Exportable cluster results for downstream health analytics

🔗 Links

• 📘 Project Notebook: Depression Risk Prediction.ipynb
• 👤 Author - Mudhassir: LinkedIn Profile

---

Feel free to ⭐ the repo if you find this helpful!