Session 2: Data Science Essentials - Harnessing the Power of Machine Learning

This CDP World 2024 user training session equips participants with the skills to create, schedule, and manage custom machine learning (ML) workflows. Attendees will gain hands-on experience using DigDag, Presto/Hivemall, and custom Python scripting to build and run ML models. The training covers best practices for designing and optimizing ML workflows, troubleshooting common issues, and ensuring data quality. Participants will explore practical use cases for custom workflows, including data cleaning or processing for improved table accuracy, running analyses or ML models, and scheduling workflows to execute in a specific sequence for efficient automation.