Online Course Supplement: Practical Data Science with Amazon SageMaker

Machine learning (ML) and Artificial Intelligence (AI) are becoming mainstream. In this course, you will spend a day in the life of a data scientist so that you can collaborate efficiently with data scientists and build applications that integrate with ML. You will learn the basic end-to-end process that data scientists use to develop ML solutions on AWS with Amazon SageMaker. You will practice the steps to build, train, and deploy an ML model to identify individuals who are most likely to benefit from the services offered by a fictitious citizen advocacy group. This course includes presentations, hands-on labs, and demonstrations.

• Preparing and processing datasets in SageMaker (e.g., using SageMaker Processing jobs, Data Wrangler for feature engineering, and notebooks in SageMaker Studio).
• Training and tuning ML models with SageMaker's built-in algorithms, custom scripts, or frameworks (e.g., via SageMaker Training jobs, Automatic Model Tuning for hyperparameter optimization).
• Deploying models to production endpoints (e.g., real-time inference with SageMaker Hosting, batch transform, A/B testing, and multi-model endpoints for efficiency).
• Monitoring, evaluating, and iterating on ML models using SageMaker tools like Model Monitor for drift detection, Clarify for bias/explainability, Experiments for tracking runs, and Pipelines for orchestration.

• Achieve practical proficiency in using Amazon SageMaker for complete ML workflows, enabling faster experimentation and deployment of models in real-world scenarios.
• Understand how to optimize SageMaker features (e.g., built-in algorithms, SageMaker Studio, Experiments, Pipelines) to solve common data science challenges with reduced manual effort.
• Be better prepared for applying SageMaker in professional or certification contexts (e.g., supporting AWS Certified Machine Learning - Specialty or data science roles), with confidence in building scalable, managed ML solutions.

• 6-hour digital course content with hands-on labs, guided exercises, code examples, and practical scenarios focused on Amazon SageMaker (supplements related theoretical courses or the main "Practical Data Science with Amazon SageMaker" series).
• Intermediate-level training in the Artificial Intelligence domain, targeted at data scientists, ML engineers, and developers with basic ML knowledge (often paired with foundational SageMaker intros).
• Emphasis on AWS-managed ML workflows, including integration with services like S3, Glue, EMR (for big data prep), and SageMaker Studio for collaborative development.
• Certificate of completion issued.