Amazon Forecast is a managed service that provides accurate future forecasts using machine learning. In this course, Time Series Forecasting with Amazon Forecast, you will learn to use Amazon Forecast and machine learning technology to create an accurate time series forecast.
First, you will explore the basics of Amazon Forecast, how it works, and how to set it up to be ready for use.
Next, you will explore how to create a target time series dataset, by creating a group dataset and understanding domains and dataset types.
Next, you will learn how to train a predictor, creating and deploying predictor queries, and obtaining and visualizing actual and predicted results in the console.
When finished with this course, you will have the skills and knowledge on how to use Amazon Forecast to create accurate future time series forecasts by using custom model predictors with machine learning algorithms to create forecasts that can be easily reviewed.
Eduardo is a technology enthusiast, software architect and customer success advocate. He's designed enterprise .NET solutions that extract, validate and automate critical business processes such as Accounts Payable and Mailroom solutions. He's a well-known specialist in the Enterprise Content Management market segment, specifically focusing on data capture & extraction and document process automation.
Course Overview Hi everyone. Welcome to my course, Time Series Forecasting with Amazon Forecast. I'm a software developer, a data capture and business automation specialist. Amazon Forecast is a fully managed service that uses machine learning to deliver highly precise forecasts based on the same technology used at amazon.com. Nowadays, organizations use everything from simple spreadsheets to complex financial planning software to attempt to forecast future business outcomes, such as product demand, resource needs or financial performance. Looking at a historical series of data can be complex. Amazon Forecast reduces this complexity as it uses machine learning to combine time series data with additional variables to build forecasts. You only need to provide historical data, plus any additional information that you believe might impact your forecasts. This helps reduce forecasting time from months to hours. Amazon Forecast is a fully managed service, so there are no servers to provision and no machine learning models to build, train or deploy. You only pay for what you use and there are no minimum fees and upfront commitments. Some of the major topics we will cover include groups and datasets, forecast domains, data preparation, building a predictor and forecast, obtaining a prediction, and comparing results. And finally, watching these technologies and principles getting applied by creating our Python scripts with some very cool demos. By the end of this course, you will know the fundamentals of working with Amazon Forecast and be able to write code that uses it. Before beginning the course, you should have some good knowledge of Python and pandas, as well as being able to find your way around Jupyter Notebooks. I hope you will join me on this journey to learn the ins and outs of the Time Series Forecasting with Amazon Forecast course, at Pluralsight.