Improve machine learning performance through effective feature engineering on Google Cloud.
The quality of a machine learning model depends on the quality of the data it learns from. This course focuses on the techniques used to create, transform, manage, and reuse features that improve model accuracy, simplify model development, and support consistent machine learning workflows across Google Cloud environments.
- Why get trained: Learn how to engineer features with Vertex AI Feature Store, BigQuery ML, TensorFlow, and Keras, while applying practical techniques for feature transformation, selection, storage, and reuse across machine learning projects.
- Why it matters: Raw data rarely produces reliable machine learning models without preparation. Well-designed features improve prediction accuracy, reduce model complexity, support consistent training, and make production machine learning systems easier to maintain and scale.
- Who should attend: Machine Learning Engineers, Data Scientists, Data Engineers, AI Engineers, Data Analysts transitioning into machine learning roles, and developers building AI solutions on Google Cloud.
Build machine learning datasets that produce more reliable models and establish repeatable feature engineering practices for production AI projects. HRD Corp Claimable.
Overview
This course explores the benefits of using Vertex AI Feature Store, how to improve the accuracy of ML models, and how to identify which data columns make the most useful features.
The curriculum includes both theoretical content and hands-on labs focused on feature engineering using BigQuery ML, Keras, and TensorFlow.
Skills Covered
Upon completion of this course, learners will be able to:
- Explain the benefits of using Vertex AI Feature Store.
- Apply feature engineering techniques to improve ML model accuracy.
- Determine which data columns are most effective as features.
- Perform feature engineering using BigQuery ML.
- Implement feature engineering workflows with Keras and TensorFlow.
Prerequisites
- Basic understanding of Machine Learning concepts
- Familiarity with SQL (for BigQuery ML) and Python (for Keras/TensorFlow)
Target Audience
- Data Scientists
- Data Analysts looking to transition into ML roles
- Aspiring or practicing Machine Learning Engineers
Module 1: Introduction to Feature Engineering
- What are features?
- Why features impact model accuracy
- Raw data vs. useful features
Module 2: Vertex AI Feature Store
- Benefits of Feature Store
- Managing, sharing, and reusing features
- Online vs. offline serving
Module 3: Feature Engineering with BigQuery ML
- Creating features from SQL queries
- Transforming data at scale
- Lab: Feature engineering in BigQuery
Module 4: Feature Engineering with Keras
- Preprocessing layers
- String lookup, discretization, normalization
- Lab: Keras feature columns
Module 5: Feature Engineering with TensorFlow
- tf.data for feature pipelines
- Feature crosses and embeddings
- Lab: TensorFlow feature engineering
Module 6: Challenge Lab (Skills Badge)
- Jump directly to a challenge lab
- Demonstrate skills without completing all modules
Dates & Locations
August 5, 2026 - August 5, 2026
August 5, 2026 - August 5, 2026
October 5, 2026 - October 5, 2026
October 5, 2026 - October 5, 2026
December 7, 2026 - December 7, 2026
December 7, 2026 - December 7, 2026
Exam & Certification
Training & Certification Guide
Frequently Asked Questions
Speak to a Training Consultant
All courses are HRD Claimable.
Get in touch with our team via the form or WhatsApp us on +6011-5119 6631
