Filter (clear filters)





Overview for Capital One

Deep-Dive on How Capital One Automates the Delivery of Directory Services Across AWS Accounts

Learn how Capital One uses AWS Managed AD to provide highly available authentication and authorization services for its Windows workloads, such as Amazon RDS for SQL Server. This talk is detailed on how Capital One uses Lambda, Python, and PowerShell with cross-account AWS Identity and Access Management (IAM) roles to automate directory deployment across AWS accounts. Also, this talk covers the best practices for integrating AWS Managed AD with your on-premises domain securely, and shows you how to automate the joining of AWS resources to your managed domain.


A Machine Learning Approach—Recommendation Engine for Real-Time Processing Use Case at Capital One

Learn how Capital One applies a Machine Learning Approach to help customers getting notified in real time on incorrect charges on their credit cards. Example of analyzing and processing over 20 million transactions per day with Capital One Streaming platform and building a machine learning model to identify merchant white and black lists for real time alerts.


Finding Bad Acorns

This talk highlights Capital One's journey to bring fraud decisioning to their tellers using Kafka, Flink and AWS Lambda. Andrew Gao and Jeff Sharpe share their learnings and experiences to common problems such as custom windowing, breaking down a monolith app to small queryable state apps, feature engineering with Jython, dealing with back pressure from combining two disparate streams, model/feature validation in a regulatory environment, and running Flink jobs on Kubernetes.


Automating Legal Fulfillment with SparkML by Brendan Herger

Learn how the Center for Machine Learning at Capital One have built a self contained platform for summarizing, filtering and triaging thousands of legal requests  they receive every year, often as physical mail. During this talk, Brendan Herger dives into how they do this , utilizing Apache projects.