💤 Sleep Health and Digital Screen Exposure Risk Prediction

A comprehensive data science project that investigates the impact of digital screen exposure on sleep health. The project combines exploratory data analysis (EDA), statistical visualizations, and machine learning techniques to identify patterns and predict sleep quality based on screen time and other lifestyle factors.

---

🎯 Project Objectives

• Explore the relationship between screen time and sleep quality.
• Visualize key correlations and trends in the dataset.
• Build machine learning models to predict sleep disruption.
• Offer actionable insights for improving digital wellness.

---

🧰 Tech Stack

---

📸 Visualizations

Here are a few visualizations used in the project:

• Goals scored per season (Bar chart)
• Win distribution by team (Pie chart)
• Heatmap of feature correlations
• Top 10 goal scorers (Horizontal bar chart)

---

🤖 Machine Learning Approach

• Preprocessing: Feature scaling, handling missing values, label encoding.
• Models Tried:
  • Logistic Regression
  • Random Forest Classifier
  • Support Vector Machine (SVM)
• Target Variable: Sleep quality level (binary or multi-class)
• Evaluation Metrics: Accuracy, Precision, Recall, F1 Score, ROC-AUC

---

🚀 Future Work

• Incorporate more advanced deep learning models (LSTM, CNN)
• Add mobile vs desktop screen usage segmentation
• Collect time-series data for sequential modeling
• Build an interactive dashboard using Plotly/Dash or Power BI

---

📁 Dataset Source

The dataset is sourced from Kaggle and contains anonymized user records including screen usage habits, sleep duration, and health indicators.

---

👤 Author

Somtirtha Chakraborty
🔗 LinkedIn
📫 Gmail