Data Science in the Enterprise
summary
ING centralizes multiple enterprise warehouses into a production Data Lake that feeds batch and streaming analytics, combining Hadoop, Spark, Cassandra, Kafka and an actor layer in Akka to deliver models and notifications. A lightweight REST wrapper called Coral spins up actors at runtime to apply models and push alerts; architecture (described as Cassandra+Spark+Akka flux capacitor) sustains petabytes of history, micro-batches down to ~2s and thousands of transactions per second for millisecond notifications, and is already deployed for compliance, fraud detection and real-time personalization.
AI-written summary · about
chapters (8)
- 0:00Introduction to data science
- 1:50ING's enterprise strategy
- 5:07Types of data in banking
- 9:22Data science use cases
- 13:39Building the data lake
- 20:00Streaming events with Spark
- 31:50Real-time customer insights
- 47:22Q&A and closing
related talks
27mData Analytics Democratization: How ING Data Analytics Platform Bootstraps New...
19mBig Data
34mThe Data Analytics Platform or How to Make Data Science in a Box Possible
46mFast Data at ING
49mData Platform Architecture, Evolution, and Philosophy
43mDevOps at ING Analytics
16mTransforming Analytics With AI: A Comprehensive Guide to an Advanced Tech Stack
29mLakeside AI: Bringing Models to Data with Open Lakehouses & Agents)