Feedzai has developed MUSE, a multi-tenant model serving framework designed to streamline model updates in binary classification systems. This framework decouples model scores from client decision boundaries, enabling dynamic routing and score transformation to maintain a stable reference distribution. MUSE has been deployed at scale by Feedzai, processing over 4,000 events per second and billions of events annually, significantly reducing model lead times from weeks to minutes and enhancing resilience against shifting attacks. AI
IMPACT Enables faster model updates in production systems, reducing operational costs and improving resilience to evolving threats.
RANK_REASON The item is a research paper detailing a new framework called MUSE. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →