This Guidance provides automakers and suppliers with a suite of modules to ingest, store, and analyze warranty data collected from dealerships across the world. Using machine learning (ML) and analytics, this Guidance predicts components that are likely to become major defects or recalls and enables customers to take corrective actions to reduce faulty inventory. You can expose these predictions with an easy-to-use dashboard, which allows you to review predicted issues, and then use insights prioritize tasks across your organization. With visibility into potential defects, you can reduce faulty inventory and warranty costs and prevent brand damage.
Architecture Diagram
[Architecture diagram description]
Step 1
Scripts running on Amazon Elastic Compute Cloud (Amazon EC2) periodically ingest automotive warranty claims from automotive portals and store them in Amazon Simple Storage Service (Amazon S3) buckets. This data then goes through scalable extract, transform, load (ETL) pipelines implemented in AWS Glue.
Step 2
Amazon Redshift, a centralized data warehouse, then hosts this data, which includes enriched data and tables for specific analytical dashboards. Amazon Redshift can scale to meet the needs of an entire enterprise or organizational unit.
Step 3
Amazon SageMaker Studio provides data scientists and analysts with a comprehensive tool chain for data exploration, model training, and machine learning operations (MLOps) pipelines, all in one place.
Step 4
The broader community of analysts and users obtain specific actionable recommendations through dashboards deployed on Amazon QuickSight.
Step 5
Amazon EventBridge initiates periodic ingestion and ML pipelines. Amazon CloudWatch provides logging and monitoring capabilities.
Step 6
Data scientists and automotive analysts iteratively develop and review analyses developed in SageMaker Studio and QuickSight dashboards.
Step 1
Scripts running on Amazon Elastic Compute Cloud (Amazon EC2) periodically ingest automotive warranty claims from automotive portals and store them in Amazon Simple Storage Service (Amazon S3) buckets. This data then goes through scalable extract, transform, load (ETL) pipelines implemented in AWS Glue.
Step 2
Amazon Redshift, a centralized data warehouse, then hosts this data, which includes enriched data and tables for specific analytical dashboards. Amazon Redshift can scale to meet the needs of an entire enterprise or organizational unit.
Step 3
Amazon SageMaker Studio provides data scientists and analysts with a comprehensive tool chain for data exploration, model training, and machine learning operations (MLOps) pipelines, all in one place.
Step 4
The broader community of analysts and users obtain specific actionable recommendations through dashboards deployed on Amazon QuickSight.
Step 5
Amazon EventBridge initiates periodic ingestion and ML pipelines. Amazon CloudWatch provides logging and monitoring capabilities.
Step 6
Data scientists and automotive analysts iteratively develop and review analyses developed in SageMaker Studio and QuickSight dashboards.
Well-Architected Pillars
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.
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
-
Operational ExcellenceRead the Operational Excellence whitepaper
This Guidance includes CloudWatch logs to help you understand system performance. You can see you are achieving your business outcomes through successful end-user content consumption.
-
SecurityRead the Security whitepaper
This Guidance uses AWS CloudFormation to deploy resources to the AWS Cloud, reducing the risk of human error during manual configuration or management. Additionally, AWS Secrets Manager stores all credentials required for connection to outside portals. AWS Identity and Access Management (IAM) roles associated with each resource in this architecture were designed according to the principle of least privilege with minimal permissions. Data in Amazon S3 and Amazon Redshift is encrypted at rest.
-
ReliabilityRead the Reliability whitepaper
This Guidance includes dependencies on external systems, which may impact the reliability of the batch ingestion process. To address this potential issue, the Guidance includes rules in CloudWatch that will prompt Amazon Simple Notification Service (Amazon SNS) to send a notification to proactively alert operations staff in the event of failures. Additionally, the architecture incorporates managed services and serverless technologies where possible for processing and exposing data.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Scalable and highly available services like Amazon S3, AWS Glue, and Amazon Redshift are purpose-built for data analytics workloads.
-
Cost OptimizationRead the Cost Optimization whitepaper
This Guidance uses managed services, such as Amazon Aurora and SageMaker, that can scale to match demand. Most of the services are also serverless, such as Amazon S3, QuickSight, and Lambda, which reduces infrastructure management and idle resources.
-
SustainabilityRead the Sustainability whitepaper
Compute and memory sizes can be right-sized at all levels of the design to minimize resource utilization. Managed services like AWS Glue and SageMaker distribute sustainability impact across all tenants of the service.
Implementation Resources
A detailed guide is provided to experiment and use within your AWS account. Each stage of building the Guidance, including deployment, usage, and cleanup, is examined to prepare it for deployment.
The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Related Content
How Machine Learning on AWS can help customers predict the risk of Automotive Part Recalls
Disclaimer
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.