End-to-End Machine Learning Project Development: Spam Classifier

Author(s): Cornellius Yudha Wijaya

Originally published on Towards AI.

Learn how to develop an ML project from development to production.

Top highlight

Photo by charlesdeluvio on Unsplash

All the code used in this article is stored in the end-to-end spam classifier repository. It’s best to clone this repository to following the article.

If we say an end-to-end machine learning project doesn't stop when it is developed, it's only halfway. A machine Learning project succeeds if the model is in production and creates continuous value for the business.

Many beginners in data science and machine learning only focus on the data analysis and model development part, which is understandable, as the other department often does the deployment process. However, creating an end-to-end machine learning project has now become a necessity.

In this article, I will provide a walkthrough for you to create a simple end-to-end machine spam classifier learning project. We will walk through it together, from the data analysis to automatic retraining. Overall, the article is structured as shown below.

1. Establish a Data Science Project2. Spam Classifier Development – EDA and Model Development – Model Development and Experiment Tracking with MLFlow3. Model Deployment with FastAPI and Docker – Spam Classifier Back-end – Spam Classifier Front-end – Combining Back-end and Front-end with Docker Compose4. Data Drift Detection and Model Retraining Trigger – Data Drift Detection with… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI