uniopen fine-tunes Nova with SageMaker for retail moderation
What happened
On 1 October 2026, the AWS Machine Learning Blog reported that uniopen used Amazon SageMaker AI to supervised fine-tune Amazon Nova 2 Lite, along with prompt-level output optimisation, to fit its own retail moderation policy. The policy classifies behaviour along two axes: nine behaviour categories and three subject types (brand, other, prohibited). The fine-tuning dataset contains 3,391 conversation windows, and three configurations were compared on a held-out test set of 737 conversation windows. The report says the approach has been deployed to production.
Written by AI from the reports · updated 26 min ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogHow uniopen customized Amazon Nova to their retail moderation policies for production deployment
uniopen is a digital communication and membership platform launched by Taiwan’s Uni-President Enterprises Group, connecting customers to ecommerce, membership benefits, and other retail experiences across web, tablet, and mobile channels. Across those channels, uniopen applies a moderation policy that classifies each interaction along two axes.
Heat of this event
Not enough continuous observations yet to draw a trend.