🛍️ Product Category Prediction using Decision Tree

👨‍💻 Author: Karne Siddhartha — Python Developer | AI / NLP Developer

A machine learning web application that predicts the product category based on product attributes such as price, weight, and customer rating.

This project demonstrates an end-to-end supervised machine learning workflow including model training, evaluation, explainability, and real-time prediction through an interactive Streamlit application.

---

🚀 Live Demo (Hugging Face)

👉 https://huggingface.co/spaces/Siddhartha001/Product_Category_Prediction_Decision_Tree

---

🧠 Model Overview

Algorithm: Decision Tree Classifier Problem Type: Multi-class Classification Goal: Learn interpretable decision rules for product categorization.

Input Features

• Price
• Weight (kg)
• Customer Rating

Output

• Predicted Product Category
• Prediction Confidence Score
• Decision Tree Visualization (Explainable AI)

Supported Categories

• Electronics
• Clothing
• Grocery

---

📊 Dataset

A small demonstration dataset is used to highlight model interpretability and decision boundaries clearly.

Price	Weight (kg)	Rating	Category
1000	1.5	4.5	Electronics
50	0.5	3.8	Clothing
10	0.3	4.8	Grocery

📌 The dataset is intentionally compact so users can visually understand how decision trees split features and make predictions.

---

⚙️ How the Application Works

1. Data is loaded and split into training and testing sets.
2. Features are used to train a Decision Tree Classifier.
3. Model performance is evaluated using accuracy metrics.
4. Users provide new product details through the UI.
5. The model predicts the category with confidence probability.
6. A visual tree diagram explains the decision path.

---

🛠 Tech Stack

• Python
• Streamlit
• Scikit-learn
• NumPy
• Pandas
• Matplotlib

---

📁 Project Structure

Product_Category_Prediction/
├── app.py                 # Streamlit ML application
├── requirements.txt       # Dependencies
└── README.md              # Project documentation

---

▶️ Run Locally

pip install -r requirements.txt
streamlit run app.py

---

🎯 Project Highlights

• Explainable Machine Learning using Decision Trees
• Interactive real-time prediction interface
• Visual interpretation of model logic
• Clean end-to-end ML pipeline structure
• Beginner-friendly yet industry-relevant design

---

👤 Author

Karne Siddhartha Python Developer | AI & Machine Learning

🤗 Hugging Face: https://huggingface.co/Siddhartha001 🔗 GitHub: https://github.com/k-siddhartha-ai

---

📌 Notes

• The dataset is simplified for educational visualization.
• The architecture can be scaled to real e-commerce datasets.
• The focus of this project is interpretability, visualization, and ML fundamentals.