Parameta Solutions (TP ICAP data arm): Generative AI extracting trade/order data from chat records with Amazon Bedrock
Parameta Solutions, the data arm of TP ICAP, used AWS Experience-Based Acceleration and Amazon Bedrock to build a production-ready generative AI solution that extracts order, price, and trade data from call and chat records among trading desks. The team built data pipelines, Amazon Bedrock orchestration, an evaluation framework, and observability, and then reused the learned components for other datasets such as speech-to-text and document extraction. The article also says Parameta monetized the resulting dataset and improved operational efficiency through automated end-of-day pricing processing.
- Organization
- Parameta Solutions
- Industry
- Finance
- Location
- United Kingdom
- Published
- May 2026
Reported outcomes
Strategic outcomes
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Parameta Solutions, TP ICAP
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Customer Stories
The article also says Parameta monetized the resulting dataset and improved operational efficiency through automated end-of-day pricing processing
Primary read
Use case focus
Showing 3 of 4
- 1Document Processing
- 2Data Extraction
- 3Workflow Automation
- Build revenue-generating generative AI solutions for extracting structured order, price, and trade data from large volumes of call/chat records.
- Automate downstream processing for commodities pricing and accelerate time to production.
- Use Amazon Bedrock to orchestrate foundation models over call and chat records.
- Build production-ready data pipelines, evaluation, and observability.
- Reuse the AWS solution patterns for speech-to-text and document extraction workloads.
- Concept-to-production readiness in a 3-week EBA engagement.
- New monetized dataset created new revenue and customer growth opportunities.
- Automated end-of-day pricing processing improved operational efficiency.
Architecture
Parameta used AWS Experience-Based Acceleration with Amazon Bedrock orchestration, data pipelines, an evaluation framework, and observability to create a production-ready generative AI solution. The solution processed call and chat records from trading desks to extract order, pricing, and trade data. The article also references reuse of AWS serverless components and adjacent workflows using Amazon Transcribe and Amazon Textract.
Sources & evidence1
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Technical implementation details available
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
Loading comments...