Fine-tuning Amazon Nova models using Amazon SageMaker AI can automate accurate data extraction from diverse email formats, addressing challenges like model hallucinations, confusion between similar data types, and high token costs. Parcel Perform, an AI Delivery Experience Platform for ecommerce businesses, collaborated with the AWS Generative AI Innovation Center to optimize Nova models. Le Vy, AI Team Lead at Parcel Perform, reported that the fine-tuned Nova Micro models achieved up to 94.77% extraction accuracy on the testing dataset, an improvement of up to 16.6 percentage points over the baseline. The fine-tuned Nova Micro reduced inference latency by more than 30 percent and halved costs compared with Parcel Perform’s previous model, while matching or exceeding the fine-tuned Nova Lite model at lower cost. Parcel Perform moved the solution into production to improve its e-commerce logistics operations. The solution uses supervised fine-tuning with Parameter-Efficient Fine-Tuning through Low-Rank Adaptation, allowing customization with limited training data and deployment into Amazon Bedrock with on-demand inference priced per token.