Real-time, Streaming Advanced Analytics....
summary
Live demos show a working pipeline that ingests clicks with NiFi→Kafka→Spark Streaming→Cassandra, trains ALS collaborative filtering (saved to Elasticsearch) and serves top‑5 recommendations in real time; ALS uses rank=10, max 20 iterations and returns the same dot‑product confidences printed in the notebook. Face experiments run PCA on the Labeled Faces in the Wild set (~1,600 images downsampled to 50×50, top 8 eigenfaces) and return surprising lookalike matches (Tom Cruise examples). Online streaming MF and automated deploys are planned but not fully productionized.
AI-written summary · about
chapters (8)
- 0:00Introduction and demo setup
- 1:59Background and past projects
- 8:21Streaming matrix factorization focus
- 12:11Live collaborative filtering demo
- 20:50Matrix factorization with ALS
- 35:50Graph-based movie recommendations
- 39:23Eigenfaces and PCA demo
- 45:02Q&A and closing
related talks
34mActionable Insights with Real-time Streaming Analytics of Customer Reviews
01h 47mRadanalytics.io streaming applications workshop
40mBuilding your own Distributed Streaming Recommendation Engine
37mBig Data Analytics, Machine Learning, Real Time Processing
26mUnleash the Power of Apache Cassandra: Scalable Recommendation Systems, Real-time Fraud Detection
41mAdding Generative AI to Real Time Streaming Pipelines
33mDo I Know You? Real time facial recognition with an Apache stack
31mAccelerating Your Analytics Journey With Real-time AI