Time Series Forecasting Principles with Amazon Forecast - Time Series Forecasting Principles with Amazon Forecast

Time Series Forecasting Principles with Amazon Forecast

Publication date: September 1, 2021 (Document history)

Companies today use everything from simple spreadsheets to complex financial planning software in a bid to accurately forecast future business outcomes such as product demand, resource needs, and financial performance. This paper introduces forecasting, its terminology, challenges, and use cases. This document uses a case study to reinforce forecasting concepts, forecasting steps, and references how Amazon Forecast can help solve the many practical challenges in real-world forecasting problems.


Forecasting is the science of predicting the future. By using historical data, businesses can understand trends, make a call on what might happen and when, and in turn, build that information into their future plans for everything from product demand to inventory planning and staffing.

Given the consequences of forecasting, accuracy matters. If a forecast is too high, customers may over-invest in products and staff, which results in wasted investment. If the forecast is too low, customers may under-invest, which leads to a shortfall in raw materials and inventory, creating a poor customer experience.

Today, businesses try to use everything from simple spreadsheets to complex demand/financial planning software to generate forecasts, but high accuracy remains elusive for two reasons:

  • First, traditional forecasts struggle to incorporate large volumes of historical data, missing important signals from the past that are lost in the noise.

  • Second, traditional forecasts rarely incorporate related but independent data, which can offer important context (such as price, holidays/events, stock-outs, marketing promotions, and so on). Without the full history and the broader context, most forecasts fail to predict the future accurately.

Amazon Forecast is a fully managed service that overcomes these problems. Amazon Forecast provides the best algorithms for the forecasting scenario at hand. It relies on modern machine learning (ML) and deep learning when appropriate to deliver highly accurate forecasts. Amazon Forecast is easy to use and requires no machine learning experience. The service automatically provides the necessary infrastructure, processes data, and builds custom/private ML models that are hosted on AWS and ready to make predictions. In addition, as advances in machine learning techniques continue to evolve at a rapid pace, Amazon Forecast incorporates these, so that customers continue to see accuracy improvements with minimal to no additional effort on their part.

Are you Well-Architected?

The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.

In the Machine Learning Lens, we focus on how to design, deploy, and architect your machine learning workloads in the AWS Cloud. This lens adds to the best practices described in the Well-Architected Framework.

For more expert guidance and best practices for your cloud architecture—reference architecture deployments, diagrams, and whitepapers—refer to the AWS Architecture Center.