📊 Customer Churn Prediction – AI SaaS Dashboard

A Machine Learning powered web application that predicts whether a customer will churn (leave a service) or stay. This project demonstrates how AI can help businesses understand customer behavior and improve retention strategies using data-driven insights.

---

🚀 Project Overview

Customer churn is one of the most important problems in subscription-based businesses. This project uses a classification-based Machine Learning model trained on customer data to predict churn probability in real-time through a modern Streamlit dashboard. The application is designed with a SaaS-style UI including login system, analytics dashboard, and interactive visualizations.

---

✨ Key Features

• 📊 Data Cleaning & Preprocessing
• 🔍 Exploratory Data Analysis (EDA)
• 🧠 Machine Learning Model Training
• 📈 Real-time Churn Prediction
• 🎨 Modern SaaS-style UI (Glassmorphism Design)
• 🔐 Login Authentication System
• 📊 Interactive Dashboard (Streamlit)
• ⚡ Visual Risk Analysis (Charts & Metrics)

---

🧠 Technologies Used

• Python 🐍
• Pandas
• NumPy
• Matplotlib / Seaborn
• Scikit-learn
• Plotly
• Streamlit

---

📌 Project Type

2. Customer Churn Prediction

Identify customers likely to leave a service or subscription.

Guidelines followed:

• Used historical customer data (usage, support calls, activity logs)
• Preprocessed imbalanced data using SMOTE
• Applied Logistic Regression, Decision Trees, and Neural Networks

---

Telvex AI Architecture

┌─────────────────────────────┐
│  Telecom Customer Dataset   │
└─────────────┬───────────────┘
              │
              ▼
┌─────────────────────────────┐
│ Data Processing & Cleaning  │
│ Pandas • NumPy              │
└─────────────┬───────────────┘
              │
              ▼
┌─────────────────────────────┐
│ Churn Intelligence Engine   │
│ Risk Scoring Logic          │
│ Revenue Exposure Analysis   │
└─────────────┬───────────────┘
              │
      ┌───────┴────────┐
      ▼                ▼
┌──────────────┐  ┌────────────────┐
│ Geo Heatmap  │  │ Risk Dashboard │
└──────┬───────┘  └────────┬───────┘
       │                   │
       └────────┬──────────┘
                ▼
┌─────────────────────────────┐
│ Telvex Streamlit Interface  │
│ Interactive SaaS Dashboard  │
└─────────────────────────────┘

---

Requirements

Before running Telvex locally, install the required Python libraries:

pip install -r requirements.txt

Core Dependencies

Library	Purpose
Streamlit	Interactive SaaS dashboard
Pandas	Data processing and analysis
NumPy	Numerical computations
Plotly	Interactive visualizations

---

📸 Screenshots

---

👤 Author

🚀 Meet Sharma

📧 meetsharma572@gmail.com