---

🎓 What is Grade Predictor?

"Your habits today are your grades tomorrow. Let the data prove it."

The Student Grade Predictor is a next-generation Academic Intelligence Engine — a production-grade Streamlit application powered by a Random Forest Regressor. It forecasts a student's final exam score by analyzing 20+ variables spanning academic habits, lifestyle patterns, and — uniquely — AI tool usage behavior.

Whether you're an educator identifying at-risk students, a student optimizing your study strategy, or an analyst researching modern learning patterns — this tool delivers data-driven academic insights wrapped in a premium glassmorphism UI.

Grade Tier	Score Range	Classification
🏆 Excellent	85 – 100	TOP PERFORMER
✅ Good	65 – 84	ON TRACK
⚠️ Needs Support	0 – 64	INTERVENTION NEEDED

---

🖼️ Preview

_{✨ Glassmorphism dark UI — where machine learning meets beautiful design}

---

🚀 Key Features

🔮 Precision Grade Forecasting Leverages a Random Forest Regressor 🌳 to predict final exam scores by modeling complex non-linear relationships across 20+ academic and lifestyle variables.	🤖 AI Usage Analytics (Unique!) Tracks the impact of ChatGPT, Gemini, and Claude on learning outcomes — evaluating AI Dependency, Ethics Score, and Prompting Frequency to distinguish healthy assistance from over-reliance.
📊 Holistic Student Profiling Covers Academic Metrics (Study Hours, Attendance, Past GPA), Lifestyle Factors (Sleep Quality, Social Media), and real-time what-if sliders for instant scenario analysis.	🎨 Premium Glassmorphism UI Translucent containers, blur effects, animated progress bars, and color-coded performance cards — all delivered inside Streamlit for a native app experience.

---

⚙️ How It Works

┌──────────────────────────────────────────────────────────────────┐
│            GRADE PREDICTOR — ML PIPELINE                         │
└──────────────────────────────────────────────────────────────────┘

  📋 USER INPUT
   └─ Academic History · Lifestyle Habits · AI Tool Usage Patterns
        │
        ▼
  🤖 AI USAGE ANALYSIS
   └─ Dependency Score · Ethics Rating · Prompting Frequency
        │
        ▼
  🔧 PREPROCESSING
   └─ Label Encoding · Feature Scaling · Distribution Alignment
        │
        ▼
  🌳 RANDOM FOREST REGRESSOR
   └─ Ensemble of decision trees → averaged score prediction
        │
        ▼
  📊 PREDICTION OUTPUT
   └─ Final Score (0–100) + Performance Tier + Visual Feedback Card

---

📈 Model Performance

Metric	Value
🌳 Algorithm	Random Forest Regressor
🎯 R² Score	0.8560
📉 Mean Absolute Error	4.1064
📐 Mean Squared Error	26.7775
🔢 Input Features	20+ variables
⚡ Inference	Real-time (< 200ms)

Key Predictor Importance (Random Forest Feature Weights)

Past Grades          ████████████████████░  ~92%
Study Consistency    ███████████████████░░  ~88%
AI Ethics Score      █████████████████░░░░  ~81%
Sleep Quality        ████████████████░░░░░  ~76%
Attendance Rate      ███████████████░░░░░░  ~72%
Social Media Usage   █████████████░░░░░░░░  ~65%

---

🛠️ Tech Stack

---

📦 Local Setup

# 1️⃣ Clone the repository
git clone <your-repo-url>
cd student-grade-predictor

# 2️⃣ Create & activate virtual environment
python -m venv venv

# Windows
.\venv\Scripts\activate
# macOS/Linux
source venv/bin/activate

# 3️⃣ Install dependencies
pip install -r requirements.txt

# 4️⃣ Launch 🚀
streamlit run app.py

Tip: The app will auto-open at http://localhost:8501 — no browser config needed.

---

🤝 Contributing

All contributions are welcome — whether it's improving model accuracy, adding new feature variables, or pushing the UI further.

1. Fork the repository
2. Create your feature branch  →  git checkout -b feature/SleepPatternAnalysis
3. Commit your changes         →  git commit -m "Add: Sleep cycle impact modeling"
4. Push to branch              →  git push origin feature/SleepPatternAnalysis
5. Open a Pull Request         →  describe your changes clearly

---

📧 Connect

Built with obsession by Salik Ahmad 🌳