https://github.com/prince2004patel/customer-churn-ann-classification

A Streamlit-powered web application for predicting customer churn using ANN. The app provides an interactive interface for data input, and churn prediction.
https://github.com/prince2004patel/customer-churn-ann-classification

artificial-neural-networks customer-churn-prediction keras machine-learning python streamlit tensorflow

Last synced: 16 days ago
JSON representation

A Streamlit-powered web application for predicting customer churn using ANN. The app provides an interactive interface for data input, and churn prediction.

• Host: GitHub
• URL: https://github.com/prince2004patel/customer-churn-ann-classification
• Owner: prince2004patel
• Created: 2025-01-17T13:57:31.000Z (20 days ago)
• Default Branch: main
• Last Pushed: 2025-01-17T14:28:59.000Z (20 days ago)
• Last Synced: 2025-01-17T15:26:12.425Z (20 days ago)
• Topics: artificial-neural-networks, customer-churn-prediction, keras, machine-learning, python, streamlit, tensorflow
• Language: Jupyter Notebook
• Homepage: https://customer-churn-ann-classification-by-prince.streamlit.app/
• Size: 448 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Customer Churn ANN Classification

## Live Demo :-

[![Streamlit App](https://img.shields.io/badge/Streamlit-App-blue)](https://customer-churn-ann-classification-by-prince.streamlit.app/)

## Basic Steps :-

### 1. Forward and Backward Propagation

- **Forward Propagation**: Passes the input data through the network to generate the output.

- **Backward Propagation**: Computes the gradient of the loss function with respect to each weight by the chain rule, updating weights to minimize the loss.

### 2. Loss Functions

- **Binary Cross-Entropy**: Used for binary classification tasks, measures the difference between the predicted probabilities and the actual labels.

### 3. Optimizers

- **Adam Optimizer**: Combines the best properties of the AdaGrad and RMSProp algorithms to handle sparse gradients and non-stationary objectives.

### 4. Activation Functions

- **ReLU (Rectified Linear Unit)**: Introduces non-linearity into the model, helps the network learn complex patterns.

- **Sigmoid**: Squashes output to a range between 0 and 1, suitable for binary classification.

## Project Overview :-

This project classifies customer churn using an Artificial Neural Network (ANN). It takes input features about customers and predicts the probability of churn.

## Setup Instructions :-

### 1. Clone the Repository

To clone the repository, use the following command:

```bash

git clone https://github.com/prince2004patel/Customer-Churn-ANN-Classification.git

```

### 2. Install Dependencies:

1. Ensure you are in the project directory:

   

```bash

cd Customer-Churn-ANN-Classification

```

2. Install all necessary Python libraries:

```bash

pip install -r requirements.txt

```

### 3. Run The Application :-

Start the Streamlit app:

```bash

pip install -r requirements.txt

```

## Some Screenshots

![Customer Churn ANN Classification](img1.png)

![Customer Churn ANN Classification](img2.png)