Haris

📱 Social Media Usage Risk Predictor

A Machine Learning web application that predicts Social Media Usage Risk Level (Low / Medium / High) based on user behavioral and demographic inputs.

🎯 Overview

This app uses a Random Forest Classifier trained on an E-commerce Customer Behavior dataset to classify users into three risk categories based on features like:

• Age & Gender
• City & Membership Type
• Total Spend & Items Purchased
• Average Rating & Satisfaction Level
• Days Since Last Purchase
• Discount Applied

🤖 Model Details

🚀 How to Run Locally

git clone https://huggingface.co/spaces/<your-username>/social-media-risk-predictor
cd social-media-risk-predictor
pip install -r requirements.txt
streamlit run app.py

📊 Dataset

Based on the E-commerce Customer Behavior Dataset.

Features include: Customer ID, Gender, Age, City, Membership Type, Total Spend, Items Purchased, Average Rating, Discount Applied, Days Since Last Purchase, and Satisfaction Level.

🛠 Tech Stack

• Python 3.10+
• Streamlit — Web interface
• Scikit-learn — ML model (Random Forest)
• Pandas / NumPy — Data processing
• Hugging Face Spaces — Deployment

📸 Screenshot

---

Built with ❤️ for ML deployment demonstration.