/Customer-Churn-HyperTuned-NeuralNetwork-PyTorch

Tuned Customer churn classification model by tuning key hyperparameters in PyTorch.

Primary LanguageJupyter NotebookMIT LicenseMIT

Hypertuned Neural Network PyTorch Model for Customer Churnwith

Aim

We focus on improving the Customer churn classification model's performance by tuning key hyperparameters such as learning rate, epochs, dropout, early stopping, and checkpoints in PyTorch.

Data Description

The dataset used in this project contains information about customer churn based on various features. It comprises 2000 rows and 15 features for predicting churn.

Tech Stack

  • Language: Python
  • Libraries: Pandas, PyTorch, Matplotlib, scikit-learn, NumPy, imblearn, pytorch

Approach

  1. Data cleaning
  2. Data preprocessing
  3. Building a sequential neural network
  4. Model training
  5. Tuning hyperparameters

Getting Started

To run this project, follow these steps:

  1. Install the required libraries listed in requirements.txt.
  2. Execute the code in the Notebook folder using Jupyter Notebook.