Unleash the Power of Apache Cassandra: Scalable Recommendation Systems, Real-time Fraud Detection
summary
Shows Apache Cassandra (via Amazon Keyspaces) as the primary operational store with concrete demos: a SageMaker pipeline that reads ~20,000 transactions, computes K-means RFM clustering, and writes five customer segments back to Keyspaces; and a serverless real-time pipeline using Kinesis → Step Functions → Amazon Fraud Detector → Lambda → Keyspaces that classifies transactions as approved / investigate / blocked and replicates results to ap-south-1. Claims: low-latency, horizontally scalable operational ML, models monitored and working live in production.
AI-written summary · about
chapters (7)
- 0:00Scalable AI with Cassandra
- 5:15Cassandra as NoSQL backend
- 7:19Demo setup choices
- 9:28Recommendation engine with SageMaker
- 14:28Real-time fraud detection
- 20:44Scaling ML models
- 21:29Q&A on Cassandra modeling
related talks
35mMission Critical Data, and Evaluating the Community in OSS Tech
19mBuild Real time, AI powered Apps
45mReal-time, Streaming Advanced Analytics....
18mKeynote: Data = AI: Leading the Future of Gen AI with Apache Cassandra
55mSolving Classical Data Analytic Task by Using Modern Distributed Databases
40mSpark Analytics on Cassandra Data
51mReal-time Fraud Detection: Challenges and Solutions
47mReal-time Fraud Detection Challenges and Solutions