Transitioning from Amazon Forecast to Amazon SageMaker Canvas

Overview

Amazon Forecast has been a reliable service for creating time series forecasts since its launch in 2019. However, with the growing demand for enhanced features, transparency, and cost-efficiency, Amazon has closed new customer access to Amazon Forecast starting July 29, 2024. Existing customers can continue using the service, but no new features will be introduced.

Introduction

AWS is encouraging users to transition to Amazon SageMaker Canvas, a low-code/no-code tool offering next-generation machine learning (ML) capabilities, including advanced time series forecasting. This blog will explore why Amazon SageMaker Canvas is a suitable alternative and guide you through the transition process. Additionally, we’ll answer some common questions to help you navigate the change smoothly.

Why Transition to Amazon SageMaker Canvas?

1. Faster Model Building and Predictions

Amazon SageMaker Canvas provides up to 50% faster model-building performance and 45% quicker predictions than Amazon Forecast. This improvement reduces the time required to develop and deploy accurate forecasts.

2. Cost-Effectiveness

Unlike Amazon Forecast, Amazon SageMaker Canvas only charges for the compute resources. This pay-as-you-go pricing ensures that businesses can make accurate predictions without incurring excessive costs.

3. Enhanced Transparency

Amazon SageMaker Canvas grants direct access to trained models and insights, such as:

• Validation data
• Model-level and item-level performance metrics
• Hyperparameters used during training

4. Unified Dataset Approach

Amazon SageMaker Canvas simplifies data preparation by requiring just one dataset instead of the multiple datasets required by Amazon Forecast. This unified approach eliminates the complexity of managing separate datasets for target time series, related time series, and item metadata.

5. Advanced Features

Amazon SageMaker Canvas includes:

• Automatic handling of missing values
• Seamless integration with external data sources like weather APIs and holiday data
• Model leaderboard for algorithm comparison
• What-if analysis for scenario planning

These features empower businesses to make better-informed decisions with less manual effort.

Transitioning from Amazon Forecast to Amazon SageMaker Canvas

AWS provides tools and resources to make this transition as seamless as possible. Here’s a step-by-step overview:

1. Data Transformation

Amazon Forecast users often work with multiple types of datasets (target time series, related time series, and item metadata). To use Amazon SageMaker Canvas, these datasets must be merged into a single dataset. You can do this by:

• Using the Amazon SageMaker Canvas UI: A drag-and-drop data flow interface makes merging datasets straightforward.
• Using Python Scripts: AWS provides sample scripts to automate the dataset transformation process.

2. Building a Forecasting Model

Once the dataset is ready, upload it to the Amazon SageMaker Canvas application via the Amazon SageMaker console. The platform leverages AutoML to train and build a forecasting model. This includes:

• Automatically selecting the best algorithm(s)
• Generating base models
• Combining top-performing models into an ensemble for higher accuracy

3. Generating and Consuming Predictions

Amazon SageMaker Canvas offers multiple ways to use the forecasting models:

• In-app predictions: Export forecasts directly to your local desktop or integrate with Amazon QuickSight for visualization.
• Real-time predictions: Deploy models to Amazon SageMaker real-time endpoints. These HTTPS endpoints allow developers to query forecasts programmatically from their applications.

4. Optional API Usage

Amazon SageMaker AutoML APIs enable data processing, model training, and deployment for users who prefer programmatic control. AWS provides detailed Jupyter notebooks on GitHub to help users implement these APIs.

Benefits of Amazon SageMaker Canvas Over Amazon Forecast

Conclusion

Transitioning from Amazon Forecast to Amazon SageMaker Canvas offers many benefits, including faster processing, lower costs, and enhanced transparency.

By embracing Amazon SageMaker Canvas, organizations can future-proof their time series forecasting capabilities, saving time and resources while gaining more insights. Whether you’re a seasoned data scientist or a business user with no coding experience, Amazon SageMaker Canvas ensures that forecasting remains accessible and impactful.

Drop a query if you have any questions regarding Amazon SageMaker Canvas and we will get back to you quickly.

About CloudThat

CloudThat is a leading provider of Cloud Training and Consulting services with a global presence in India, the USA, Asia, Europe, and Africa. Specializing in AWS, Microsoft Azure, GCP, VMware, Databricks, and more, the company serves mid-market and enterprise clients, offering comprehensive expertise in Cloud Migration, Data Platforms, DevOps, IoT, AI/ML, and more.

CloudThat is the first Indian Company to win the prestigious Microsoft Partner 2024 Award and is recognized as a top-tier partner with AWS and Microsoft, including the prestigious ‘Think Big’ partner award from AWS and the Microsoft Superstars FY 2023 award in Asia & India. Having trained 650k+ professionals in 500+ cloud certifications and completed 300+ consulting projects globally, CloudThat is an official AWS Advanced Consulting Partner, Microsoft Gold Partner, AWS Training Partner, AWS Migration Partner, AWS Data and Analytics Partner, AWS DevOps Competency Partner, AWS GenAI Competency Partner, Amazon QuickSight Service Delivery Partner, Amazon EKS Service Delivery Partner,  AWS Microsoft Workload Partners, Amazon EC2 Service Delivery Partner, Amazon ECS Service Delivery Partner, AWS Glue Service Delivery Partner, Amazon Redshift Service Delivery Partner, AWS Control Tower Service Delivery Partner, AWS WAF Service Delivery Partner, Amazon CloudFront and many more.

To get started, go through our Consultancy page and Managed Services Package, CloudThat’s offerings.