You have created and trained a machine learning model with KNIME Analytics Platform. But how to put it into production so that it can produce predictions? In this course, we will show you how to use KNIME Software to test and deploy a prediction workflow, automate its deployment and enable the subsequent continuous deployments, monitoring, and maintenance.
We will use a credit scoring use case as an example to demonstrate how to deploy a prediction workflow manually, automatically, or continuously, and how to generate predictions via a data app or via a REST service.
In the first session of this course, you will learn how to prepare a prediction workflow for deployment. In the second session, you will be introduced to KNIME Business Hub and will learn how to deploy a prediction workflow as a data app or as a REST service. Next, in the third session, you will learn how to use the Continuous Deployment for Data Science (CDDS) extension to enable continuous deployment on KNIME Business Hub. Finally, in the fourth session, you will learn about monitoring machine learning models, and about the best practices to productionize machine learning models, such as, experiment logging and tracking, performance optimization, AutoML, and XAI.
This is an instructor-led course consisting of four, 75-minutes online sessions run by our KNIME data scientists and solution engineers. Each session has an exercise for you to complete at home and together, we will go through the solution at the start of the following session. The course concludes with a 15 to 30-minute wrap up session.
Course Content:
- Session 1: Preparing a Prediction Workflow for Deployment
- Session 2: Introduction to KNIME Business Hub
- Session 3: Continuous Deployment for Data Science
- Session 4: Best Practices when Productionizing Data Science
- Session 5: Optional follow-up Q&A (15-30min)
FAQ
You first need to create an account on the KNIME Learning Store. After you log on to the KNIME Learning Store, clicking on the “Register now” button will take you to the course web page.
You should already know how to build workflows using KNIME Analytics Platform. This course doesn’t provide an introduction to KNIME Analytics Platform - it focuses on more advanced concepts of automating and building workflows.
You can join the course using the Zoom links found in your LearnUpon course page. Please note that each Zoom link is specific to a particular session. Make sure you have a stable internet connection!
Sure! The sessions will be recorded and you’ll have access to each one for one month from the time the session is over.
Absolutely - fire away!
Your own laptop, ideally pre-installed with the latest version of KNIME Analytics Platform, which can be downloaded here: knime.com/downloads
Although our course materials are based on KNIME Analytics Platform Version 5, you can still learn different concepts and associated nodes introduced in this course. Please note that some nodes introduced in Version 5 may not be available in Version 4.
You will be granted temporary access to KNIME Business Hub during this course to work on exercises. The credential to access KNIME Business Hub will be given to you on the first day of the course. You do not need to use your organization’s KNIME Business Hub for this course.
Check out our Self-paced courses, KNIME Books, Cheat Sheets, KNIME Forum, and KNIME Hub.