Vertex Forecasting and Time Series in Practice
This course is an introduction to building forecasting solutions with Google Cloud. You start with sequence models and time series foundations. You then walk through an end-to-end workflow: from data preparation to model development and deployment with Vertex AI. Finally, you learn the lessons and tips from a retail use case and apply the knowledge by building your own forecasting models.
- Duration: 1 day
- Languages: English, German
- Level: Advanced
- Group size: Up to 16
What you'll learn
- Understand the main concepts and the applications of a sequence model, time series, and forecasting.
- Identify the options to develop a forecasting model on Google Cloud.
- Describe the workflow to develop a forecasting model by using Vertex AI.
- Prepare data (including ingestion and feature engineering) by using BigQuery and Vertex managed datasets.
- Train a forecasting model and evaluate the performance by using AutoML.
- Deploy and monitor a forecasting model by using Vertex AI Pipelines.
- Build a forecasting solution from end-to-end using a retail dataset.
Prerequisites
- Basic knowledge of Python syntax
- Basic understanding of machine learning models
- Prior experience building machine learning solutions on Google Cloud
Course outline
Course Introduction
- This module addresses the reasons to build a forecasting solution on Google Cloud and introduces the learning objectives.
Time Series and Forecasting Fundamentals
- This module provides a theoretical foundation of types of sequence models, time series patterns and analysis, and forecasting notations.
Forecasting Options on Google Cloud
- This module introduces two major options to build a forecasting solution on Google Cloud: BigQuery ML and Vertex AI Forecast (AutoML). It also investigates the unique features of Vertex AI Forecast and explores an end-to-end workflow with AutoML.
Data Preparation
- This module explores the transformation of original data to the data types and format supported by Vertex AI. It also introduces the different types of features in time series and the best practices for data ingestion.
Model Training
- This module walks learners through the model training and demonstrates them configuration details such as the setup of context window, forecast horizon, and optimization objective.
Model Evaluation
- This module describes the training data split, demonstrates the evaluation metrics, and recommends the approaches to improve the model performance.
Model Deployment
- This module demonstrates model prediction, specifically the batch prediction with Vertex AI Forecast. It also explores machine learning operations (MLOps) and the transition from development to production.
Model Monitoring
- This module describes model drift and the approach of model retraining. It also demonstrates the automation of the forecasting workflow by using Vertex AI Pipelines.
Vertex Forecasting in Retail
- This module describes a use case to build a forecasting solution with Vertex AI Forecast in a retail store. It demonstrates the steps and considerations, walks through a pilot study with two different datasets, and discusses the challenges and lessons.
Course Summary
- This module addresses the main features of Vertex AI Forecast and summarizes the main topics of each module.
Related courses
Deploy multi-agent systems with Agent Development Kit and Agent Engine
In this course, you’ll learn to use the Google Agent Development Kit to build complex, multi-agent systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You’ll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.
Generative AI in Production
Traditional MLOps is a set of practices to productionize traditional ML systems for enterprise applications. Generative AI raises new challenges in managing and productionizing applications at scale. The field of generative AI operations seeks to address these new challenges. In this course, you learn about the challenges that arise when deploying and productionizing generative AI-powered applications. You learn how to secure your generative AI-powered applications. Finally, you will discuss best practices for logging and monitoring your generative AI-powered applications in production.
Agent Observability on Google Cloud
This course provides an applied, intermediate guide to operationalizing AI agents, focusing specifically on achieving production confidence and cost predictability for Gemini-powered workflows on Google Cloud. Participants will learn the methodology and actionable skills necessary to transform non-deterministic agent logic into transparent, auditable, and scalable systems.The course covers core operational disciplines, including mapping the agent's complex thought process (ReAct loops) to Cloud Trace Spans for debugging, implementing Logs-Based Security Metrics for compliance, and setting up actionable alerts and custom dashboards in Cloud Monitoring to proactively control cost overruns and quality drift. The course uses presentations, Visual Walkthroughs, and strategic discussions to ensure effective learning that is directly applicable to the Vertex AI ecosystem
Not sure which course fits?
Book a 30-minute call. We'll look at where your team is, what they need to be able to do, and put together either a specific course date or a tailored learning plan.