Home icon

How London Stock Exchange Group is detecting market abuse with their AI-powered Surveillance Guide on Amazon Bedrock

Machine Learning Blog



London Stock Exchange Group (LSEG) has developed an AI-powered Surveillance Guide using Amazon Bedrock to improve market abuse detection and surveillance operations.

  • Uses Anthropic's Claude Sonnet 3.5 model to analyze news articles
  • Automatically predicts the probability of news being price sensitive
  • Processes approximately 250,000 RNS articles over 6 months
  • Achieved 100% precision in identifying non-sensitive news
  • Provides automated analysis with detailed classification justifications

The solution reduces manual review time for analysts, improves assessment consistency, and enables faster response to potential market abuse cases by leveraging generative AI technology.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Apr 1
2024
London Stock Exchange Group uses chaos engineering on AWS to improve resilience
Nov 19
2025
How Amazon uses AI agents to support compliance screening of billions of transactions per day
Jan 7
2025
London Stock Exchange Group uses Amazon Q Business to enhance post-trade client services
Jul 1
2024
How London Stock Exchange Group optimised blue/green deployments for Amazon Aurora PostgreSQL Global Database

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.