# 🏡 Fuzzy House Pricing

This project applies **Fuzzy Logic** to predict house prices based on uncertain or imprecise input variables such as location, area, and condition.

Fuzzy logic allows for reasoning with vague concepts like "large", "medium", or "near center" — making it well-suited for complex, real-world decision-making like real estate valuation.

---

## 💡 Why Fuzzy Logic?

- Traditional models rely on precise input (e.g., 120m² = $150,000)
- Fuzzy logic works with **linguistic terms** (e.g., "medium area", "good condition")
- Human-like reasoning mimics expert appraisers

---

## 🧠 Model Components

- **Inputs**:
  - Distance to city center (km)
  - House area (m²)
  - Condition score (0–10)

- **Output**:
  - Predicted house price (in currency unit)

- **Tech stack**:
  - Python, NumPy, scikit-fuzzy
  - Visualizations with Matplotlib
  - Interactive development via Jupyter Notebook

---

## 📊 Fuzzy Membership Functions

| Variable       | Linguistic Terms               |
|----------------|--------------------------------|
| Area           | Small, Medium, Large           |
| Distance       | Near, Moderate, Far            |
| Condition      | Poor, Average, Good            |
| Price (Output) | Cheap, Moderate, Expensive     |

---

## 🚀 Run the Notebook

1. Clone the repo:
   ```bash
   git clone https://github.com/DoNguyenAnhTuan/Fuzzy-House-Pricing.git
   cd Fuzzy-House-Pricing

2. Install dependencies:

   pip install -r requirements.txt

3. Launch the notebook:

   jupyter notebook

---

📎 Sample Output

• Input: 85m², 5km from center, condition = 7
• Output: Moderately expensive

---

📬 Author

Do Nguyen Anh Tuan 📍 MSc in IT @ Lac Hong University 🔗 Portfolio Website 🐙 GitHub