post
https://api.mbd.xyz/v3/studio/scoring/ranking_model/
Rerank a list of item IDs for a given user using an AWS Personalize campaign.
This endpoint sends the user and items to a trained AWS Personalize model, which returns the same items in a personalized order based on predicted relevance.
Flow:
- Provide
user_idanditem_idsin the request body - The service calls AWS Personalize
get_personalized_rankingwith the campaign ARN for the givenmodel_name - Response returns the same item IDs in a new order (personalized ranking)
Available Models:
polymarket-rerank-v1— Polymarket reranking campaign trained on trading activity data
Error Handling:
Errors are returned with HTTP 200 and an error field in the response body (rather than HTTP error codes). This includes:
- Missing
user_idoritem_ids - Unknown
model_name - AWS errors (campaign not found, invalid input, network issues)
