https://github.com/fadeldnswr/customer-churn-prediction
This is an End to End Deep Learning project that predicts customer churn with the use of Artificial Neural Network Model. The project uses streamlit to deploy as an interactive dashboard
https://github.com/fadeldnswr/customer-churn-prediction
artificial-neural-networks customer-churn-prediction deep-learning deep-neural-networks python streamlit tensorflow
Last synced: 4 months ago
JSON representation
This is an End to End Deep Learning project that predicts customer churn with the use of Artificial Neural Network Model. The project uses streamlit to deploy as an interactive dashboard
- Host: GitHub
- URL: https://github.com/fadeldnswr/customer-churn-prediction
- Owner: fadeldnswr
- Created: 2025-06-15T12:39:50.000Z (4 months ago)
- Default Branch: master
- Last Pushed: 2025-06-15T14:01:47.000Z (4 months ago)
- Last Synced: 2025-06-15T14:48:54.599Z (4 months ago)
- Topics: artificial-neural-networks, customer-churn-prediction, deep-learning, deep-neural-networks, python, streamlit, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 430 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Customer Churn Prediction 🧠📉
A deep learning project that leverages Artificial Neural Networks (ANN) to predict customer churn in a telecom dataset. This project is deployed as an interactive web application using Streamlit, enabling users to easily input customer data and obtain churn predictions in real-time.
## Project Overview
Customer churn is a critical KPI in many industries, especially telecommunications. Retaining existing customers is significantly more cost-effective than acquiring new ones. This project aims to build a robust predictive model using deep learning to anticipate customer churn based on behavioral and demographic features.
### Key Features
- Deep Learning Model (ANN) implemented with TensorFlow/Keras
- Preprocessing pipeline with label encoding, scaling, and balancing
- Streamlit Web App for real-time predictions
- User-friendly interface for manual input or batch prediction
- Model evaluation metrics (accuracy, confusion matrix, etc.)
## Dataset
- The dataset used in this project is a customer churn dataset sourced from a telecom company. It includes features such as:
- Demographics: Gender, Age, SeniorCitizen, etc.
- Services signed up: InternetService, OnlineSecurity, etc.
- Account information: Tenure, MonthlyCharges, TotalCharges
- Target variable: Churn (Yes/No)
## Model Architecture
The ANN model consists of:
- Input layer: Normalized input features
- Hidden layers: Multiple dense layers with ReLU activation
- Output layer: Sigmoid activation for binary classification
Compiled with:
- Loss function: binary_crossentropy
- Optimizer: adam
- Metrics: accuracy
## Deployment
The model is deployed using Streamlit, making it accessible via a simple web interface.
Try the web app locally:
```bash streamlit run app.py ```
## Requirements
Install dependencies:
```pip install -r requirements.txt ```