FindAUseCase.com
Back to Directory

Amazon EC2

7 use cases using this technology

7published use cases
6industries
5countries on record
Predictive Analytics
top AI capability

Evidence mix: High 7 · Medium 0 · Low 0 — bands are computed from each record's evidence signals.

Industry
Country

7 use cases

ManufacturingComputer VisionPredictive Analytics

ŠKODA's MAGIC EYE computer vision system predicts and prevents production line breakdowns

ŠKODA AUTO built MAGIC EYE, a computer-vision predictive maintenance system, using AWS Internet of Things services and in-house technology to move from a reactive to a proactive approach to assembly line breakdowns. Six cameras mounted by a conveyor frame collect nearly 450,000 photos as a car moves through the production line, and 10 artificial neural networks analyze them to detect irregularities such as dirt, loose or cracked bolts, or aluminum track damage, alerting a maintenance operator. The neural networks can recognize 14 defect types and 178 classes, and AWS lists reduced assembly line downtime and increased staff productivity among the benefits.

ŠKODA AUTO· Czech RepublicAmazon S3 · Amazon EC2 · Amazon RDS +1
AutomotiveComputer VisionSpeech & Audio AIPredictive Analytics

BMW Group uses AI-powered vision and sound analytics for predictive maintenance and quality management

The BMW Group built its Vision and Sound Analytics Service (VSAS) on AWS, processing 1.3 million image and audio files daily across 1.3 PB of data at more than 16 production sites worldwide. The company uses the platform's stored data to build AI models for predictive maintenance and quality management, including a computer vision model that predicts potential rail failures to reduce downtime, and an Acoustic Analytics application that automatically captures and analyzes vehicle sounds using trained models to detect anomalies and improve engine performance and in-cabin comfort, reducing the need for human intervention in testing vehicles with no driver present. Using AWS Graviton processors for AI model training, BMW cut compute costs for its computer vision solution by 63% and reduced model training time for various use cases from days to hours.

BMW GroupAmazon EC2 · Amazon S3 · Amazon OpenSearch Service +4
Financial ServicesGenerative AIComputer VisionDocument Intelligence

Empowering Employees to Work Strategically Using Amazon Bedrock with BDM

Big Data Mining (BDM), a Brazilian company, built LOUIS, a bespoke generative AI model on Amazon Bedrock combining computer vision and natural language processing to process complex, unstructured corporate documents (contracts, powers of attorney) across more than 100 models and 15 industries. A large Brazilian financial institution deployed LOUIS to replace a team of 150 professionals manually evaluating over 40,000 unstructured processes per month for opening legal-entity accounts and contracting credit, standardizing interpretation criteria and reducing operational effort by more than 40%, an estimated $4.2 million in cost savings over five years. In insurance, LOUIS reduced life insurance claim processing from up to six months to just a few minutes by capturing required data in about 60 seconds. BDM reports documents are processed 85% faster than manual interpretation with 98% accuracy, and saved roughly 50% on development costs by building on Amazon Bedrock rather than writing the application from scratch.

Big Data Mining (BDM)· BrazilAmazon Bedrock · Amazon S3 · Amazon EC2 +1
Financial ServicesGenerative AIPredictive Analytics

Discover Financial Services Builds a Generative AI Solution on AWS for Faster Decision-Making and Time to Market

Discover Financial Services, a digital banking and payment services company, built an analytics workbench and unified data science workbench on Amazon EC2 (P3 and P4 GPU instances) so its data scientists could run machine learning and generative AI workloads, train large language models with sample sizes requiring up to 6 TB of memory, and deliver high-performance computing in the cloud. Model artifacts are stored in Amazon S3 and shared across engineering teams via Amazon EFS. Discover used the platform for use cases including sentiment analysis of customer service calls and a 'do not contact' model that classifies customers in near real time for customer care agents. Using feature embedding, the team reduced time to market from hours to minutes; parallel model training cut processing of 30 million records from days to hours, and sentiment analysis on a 57,000-record dataset dropped from hours to minutes. Discover reports 35% reduction in engineering and platform costs.

Discover Financial Services· United StatesAmazon EC2 · Amazon S3 · Amazon EFS