Explore how PyCaret, a low-code Python library, can simplify and streamline the process of managing machine learning models. This session demonstrates practical automation in the ML lifecycle—making advanced model management accessible with minimal coding.
Machine learning model management often requires deep technical expertise and significant coding efforts. PyCaret, however, removes much of this friction by offering a low-code, user-friendly interface that empowers data practitioners and engineers to quickly build, compare, and deploy machine learning models.
This talk begins with an introduction to the challenges of traditional ML workflows and how PyCaret is changing the landscape. Through engaging live demonstrations, you’ll observe the full process: from loading the classic diabetes dataset, training models across a suite of algorithms, effortlessly comparing their performance, and then saving and utilizing the optimal model for practical use.
Whether you’re an aspiring data scientist or an experienced professional seeking to enhance productivity and model quality, this session provides clear, actionable guidance on getting started with PyCaret. You'll also learn how PyCaret integrates into broader ML production pipelines and how it compares to other automation tools in the ecosystem.
Join us for a fast-paced, results-oriented talk that brings the power of automated ML within everyone’s reach.
Table of Contents
Introduction to ML and PyCaret
Live Demo: Train with Diabetes Data Set using Multiple Algorithms
Live Demo: Compare Models and Select the Best One
Live Demo: Saving and Using the Model
Q&A
Gain practical experience in automating ML workflows with PyCaret
Understand end-to-end model training, comparison, and deployment—code-light!
Learn how to save, reuse, and share models for reproducible results
Discover the pros, cons, and production readiness of low-code ML solutions
Be empowered to apply PyCaret tools immediately in your projects