Steel Plate Fault Detection

🔹 A Machine Learning project to detect defects in steel plates.
🔹 Dataset: Steel Plate Faults (UCI Repository).
🔹 Models used: Logistic Regression, Decision Tree, Random Forest, SVM.
🔹 Best Accuracy: Random Forest (~94%).

Tech Stack

• Python, Pandas, NumPy
• Matplotlib, Seaborn
• Scikit-learn

How to Run

git clone https://github.com/sneha842/Steel-Plate-Defect-Prediction-Project.git
cd Steel-Plate-Defect-Prediction-Project
pip install -r requirements.txt
jupyter notebook

## 📊 Results  

- **Logistic Regression** → Accuracy ~ 82%  
- **Decision Tree** → Accuracy ~ 88%  
- **Random Forest** → Accuracy ~ 94% (Best)  
- **SVM** → Accuracy ~ 90%  

✅ Random Forest performed the best for defect classification.