Explore the critical aspects of model inference in the finance sector through this 30-minute conference talk from MLOps World: Machine Learning in Production. Delve into Capital One's approach to deploying machine learning models in production environments, focusing on the challenges of high resilience and low latency service response. Learn how Seldon V2 addresses these demands, enabling crucial business applications like credit decisions and fraud detection. Gain insights from Vincent David, Senior Director of Machine Learning, and Michael Meredith, Lead Software Engineer at Capital One, as they discuss the implementation of service-oriented architectures for model inference in the fintech industry.
Low-latency Model Inference in Finance - A Close Look at Seldon V2
MLOps World: Machine Learning in Production via YouTube
Overview
Syllabus
Low-latency Model Inference in Finance - A close look at Seldon V2
Taught by
MLOps World: Machine Learning in Production
Related Courses
-
Building a Reproducible Model Workflow
-
Inference on KubeEdge
-
Production ML Serving and Monitoring with Kubernetes
-
Learning from Extremes: What Fraud-Fighting at Scale Can Teach Us About MLOps Across Domains
-
AI Inference Workloads - Solving MLOps Challenges in Production
-
Serverless Machine Learning Inference with KFServing
