Churn prediction

Keywords: Churn, Prediction

Background

The prediction of churn in bank customers is a very important task in customer relationship management where one must identify the customer who is likely to exit the bank. The dataset contains a feature called ‘exited’ which says about whether the customer will continue with the bank, or they will leave the bank in coming days. There are other features like credit score, gender, age, tenure, salary, and others which will be used to train the model to make the predictions. The main goal is to develop a model that ca predicts the customer churn accurately based on the features. The challenge in this dataset is to handle missing values and analyze the numerical data to make it ready for training the model. The problem statement in this project is to identify the important features and build a neural network model that can predict the customer’s churn based on the available data. We used Artificial Neural Networks (ANN) algorithm which is part of deep learning to find the non-linear relationships in the dataset. The ANN model will be trained using the given data to predict the target variable by achieving the best possible accuracy.

Aim & Objectives

Aim
To predict the Churn Data Using DL Techniques
Objective
Develop a deep learning model to predict customer churn using relevant data.
Train the model with historical records for accurate churn classification.
Evaluate the model's performance to provide dependable churn predictions using DL techniques.

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —