MONTHLY EDITION

Often, the last step of a Data Science task is deployment. Let’s say you’re working at a big corporation. You’re building a project for a customer of the corporation and you’ve created a model that performs well. Unfortunately, the model you’ve created will only be able to be used by the customer if the customer has the code you’ve written, the environment you’ve created, and the machines you’ve been working on.
HOWEVER, if you deploy your model into production, the only thing the customer will need is…the product. In other words, a machine learning model will provide real value when it is available to the users that it has been created for. Your model is only a proof of concept (PoC) until it is put into production, then it becomes a deliverable.
There are many ways to deploy a Machine Learning model. The basic idea of deployment involves allowing an end-user to utilize your model. The product needs to be customized to the end user’s needs since they will be the ones who will use it. Deployment is a crucial step because it allows others to use the machine learning model that was built.
Choosing how to deploy your model into production can be difficult and you’ll need to evaluate what the end-users want and need. Perhaps your model needs to work in real time. Maybe it needs to be used to make many predictions at a time. You might need a particular architecture, etc. There can be many many requirements for a product, and more importantly, it will need to work on all use-cases, which is why debugging your model is essential.
Michael Armanious, Editor at Towards Data Science.
Why we deploy machine learning models with Go – not Python
by Caleb Kaiser – 5 min read
There’s more to production machine learning than Python scripts
Develop a NLP Model in Python & Deploy It with Flask, Step by Step
by Susan Li – 6 min read
Flask API, Document Classification, Spam Filter
There are two very different ways to deploy ML models, here’s both
by Tom Grek – 9 min read
If an ML model makes a prediction in Jupyter, is anyone around to hear it?
Quickly Build and Deploy a Dashboard with Streamlit
by Maarten Grootendorst – 7 min read
Deploying your Streamlit application to Heroku to showcase your Data Solution
Build and deploy your first machine learning web app
by Moez Ali – 11 min read
A beginner’s guide to train and deploy machine learning pipelines in Python using PyCaret
Building a Web Application to Deploy Machine Learning Models
by Joseph Lee Wei En – 19 min read
So we’ve built our ML model – now what? How to get out of Jupyter Notebook and into Web Apps with Flask!
How to Use Angular To Deploy TensorFlow Web Apps
by James Briggs
Using Python-built models in Angular-built web apps
Let’s Deploy a Machine Learning Model
by Dario Radečić – 5 min read
How to use machine learning models in production
New videos
- Determining Which ML Technologies To Act On | T. Pillai, S. Gandrabur, O. Shai & T. Poutanen
- Panel: Creative Ways to Collect & Use Data for AI | H. Ngo, S. Sun, H. Kontozopoulos, and R. Tabrizi
New podcasts
- Jakob Foerster – Multi-agent reinforcement learning and the future of AI
- Kenny Ning – Is data science merging with data engineering?
- Ihab Ilyas – Data cleaning is finally being automated
- Goku Mohandas – Industry research and how to show off your projects
We also thank all the great new writers who joined us recently Jodie Zhou, Kamila Hamalcikova, Kimoon Kim, Ron Sielinski, Nils Flaschel, Matt, Ewan Davies, Dani Solis, Boon Yang, Steve Leven, Ph.D, Farhan Rahman, Stefano Bosisio, Victor Mariano Leite, Robin White, Andreas Kanz, Grzegorz Meller, Pavan Kumar Boinapalli, Alexey Khrustalev, Pratick Roy, Jason O. Jensen, Drew Seewald, José Herazo and many others. We invite you to take a look at their profiles and check out their work.