AWS enables Parcel Perform to fine-tune Amazon Nova models for 50% cost reduction

AWS has detailed how Parcel Perform, an e-commerce logistics company, successfully fine-tuned Amazon Nova models to improve email data extraction. By leveraging Amazon SageMaker AI and Parameter-Efficient Fine-Tuning (PEFT) with Low-Rank Adaptation (LoRA), Parcel Perform achieved up to 94.77% extraction accuracy, a significant improvement over their baseline. This fine-tuning process also reduced inference latency by over 30% and cut costs by 50%, enabling them to move the solution into production for more efficient operations. AI

IMPACT Demonstrates how fine-tuning cloud-based LLMs can significantly improve accuracy and reduce costs for specialized data extraction tasks.

RANK_REASON Article describes a specific company's use of a cloud provider's AI tools for a specific task, not a new model release or core research.

Read on AWS Machine Learning Blog →

• Amazon Bedrock
• Amazon Nova
• Amazon SageMaker AI
• AWS
• Low-Rank Adaptation
• Parameter-Efficient Fine-Tuning
• Parcel Perform

• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →