Overview

As machine learning adoption grows across industries, automated machine learning (AutoML) platforms are becoming essential for accelerating model development and improving productivity. This course equips you with the practical skills to build, evaluate, optimize, and deploy ML models using H2O AutoML which is one of the most widely adopted open-source automated machine learning platforms. Using H2O, you can start producing results from day one. Throughout this course, you’ll explore the full AutoML lifecycle and discover how automated pipelines are replacing the trial-and-error approach to model development. Each concept is reinforced through step-by-step video demonstrations using H2O AutoML and H2O Flow that you can follow along and practice at your own pace. By the end of this course, you’ll be able to: • Explain what AutoML is, run baseline experiments, and interpret H2O leaderboards for model selection. • Prepare data for automated model selection, diagnose feature quality, and prevent data leakage. • Control model search using constraints and ensembles, and evaluate models using metrics like RMSE, AUC, and Logloss. • Optimize hyperparameters with structured grid search strategies and deploy models via MOJO artifacts for real-time and batch scoring. • Execute the full AutoML lifecycle through H2O Flow, a no-code visual interface, without writing a single line of code. This course is designed for a diverse audience: undergraduate students in engineering, computer science, and data science, working professionals modernizing their ML workflows, business analysts exploring data-driven decision-making, and anyone looking to gain practical machine learning skills with an automated, structured approach. Prior familiarity with basic data concepts and Python is helpful, though the course includes a dedicated no-code module using H2O Flow for learners without programming experience. Take the first step toward automated machine learning mastery and build the skills needed to deliver production-ready ML solutions using H2O AutoML.

Syllabus

Automated Machine Learning (AutoML) Essentials

Develop a clear mental model of AutoML and its emergence from the scaling limits of manual ML workflows. You will define AutoML as a structured experimentation system and understand H2O AutoML’s execution architecture. Finally, you will run and interpret your first baseline AutoML workflow.

Building Automated ML Pipelines with H2O AutoML

Explore the operational core of AutoML: data readiness, model search, and metric-driven evaluation. You will assess data requirements, recognize automation limits, and interpret leaderboards and feature importance as decision evidence. You will frame model selection as a search problem, evaluate ensemble performance, and use metrics as optimization signals.

Optimizing and Operationalizing AutoML Systems

Shift to production-ready AutoML systems. You will conduct structured hyperparameter searches, compare configurations using metrics, and apply controls such as early stopping and checkpointing for reproducible tuning. You will then deploy models via MOJO/POJO, implement scalable scoring patterns, and execute the lifecycle in H2O Flow for inspection.

Course Wrap-Up and Assessment

Integrate the complete AutoML lifecycle through an end-to-end workflow design and final assessment. You will translate course concepts into a coherent solution covering data preparation, model selection, evaluation strategy, and operational considerations. You will justify decisions using metric evidence, trade-off analysis, and established best practices.