Last updated: February 1, 2023
For a given customer's historical data, we are asked to predict whether a customer will stop using a company's product or not. We will be using the Telco Customer Churn dataset for building an end-to-end production-grade machine learning system that can predict whether the customer will stay loyal or not. The dataset has 20 input features and a target variable for 7043 customers.
This project structure including the stack and components can be used on occasions you need to construct ML pipelines for tabular data ML problems.
This project uses the following Stack Components:
- Orchestrator - Kubeflow.
- Artifact Store - Amazon Simple Cloud Storage (S3).
- Container Registry - Amazon Elastic Container Registry.
- Secret Manager - AWS Secrets Manager.
- Model Deployer - Seldon Core.
The codes to reproduce this project are open-source on GitHub. View the code here.
The detailed write-up of this project is in the following blog.