Introduction to Vertex Forecasting and Time Series in Practice

Course Introduction: This module provides an overview of the course and its objectives. It is followed by a reading list to prepare you for the upcoming content.

Time Series and Forecasting Fundamentals: This module covers essential topics such as sequence models, time series patterns, analysis, and forecasting notations. It concludes with a quiz to test your understanding.

Forecasting Options on Google Cloud: This module introduces various options to develop forecasting models on Google Cloud, including BigQuery ML and Vertex AI. It also includes a lab for hands-on experience in building a demand forecasting model using BigQuery ML.

Data Preparation: This module focuses on the crucial step of preparing data for forecasting models, covering data upload, conversion, feature engineering, and best practices. It also includes a quiz to assess your knowledge.

Model Training: This module delves into the training setup, context window, forecast horizon, and optimization objectives. It also includes a lab for training a model using Vertex AI Forecast.

Model Evaluation: This module covers aspects such as training data split, backtesting, evaluation metrics, and model improvement, providing a comprehensive understanding of model evaluation techniques.

Model Deployment: This module focuses on MLOps with Vertex AI Pipelines, making and using predictions, and concludes with a quiz to reinforce your learning.

Model Monitoring: This module addresses model drift, retraining, and pipeline automation, offering insights into the crucial aspect of monitoring forecasting models.

Vertex Forecasting in Retail: This module provides insights into a retail use case background, steps, considerations, and lessons learned, culminating in a lab to develop an end-to-end forecasting solution in the retail sector.

Summary: This module offers a comprehensive summary of the course, ensuring a thorough understanding of the key concepts and learnings from the entire course.