📊 Customer Churn Prediction - Deep Learning Model

📌 Overview

This project focuses on predicting customer churn using a Machine Learning model trained on the Churn_Modelling dataset. It leverages feature engineering, data preprocessing, and model evaluation to provide accurate predictions on whether a customer is likely to churn or not.

🔍 Key Features

📊 Data Preprocessing:

Handles missing values and categorical encoding.

Standardizes numerical features.

🚀 Feature Engineering:

Extracts key insights from customer demographics and transaction data.

Applies one-hot encoding and feature scaling.

🤖 Model Training & Evaluation:

Trains models such as Logistic Regression, Random Forest, and Neural Networks.

Evaluates performance using ROC-AUC, precision, and recall metrics.

📉 Churn Prediction:

Provides probabilities for customer churn.

Generates feature importance insights for decision-making.

📂 Files in this Repository

File

Description

Churn_Modelling.ipynb

Jupyter Notebook with full ML model implementation.