Particle Swarm Classification for Next-Gen Recommendation Engines
summary
Claims an optimal recommendations engine for consumer banking that yields high-response tailored results from anonymized and incomplete data and actually ships it. Implementation uses quantum particle swarm optimization techniques plus a homegrown knowledge representation graph, backed by Delta Lake/Databricks, MLflow model registry, Terraform templates, real-time feature store and Apache Soda for data quality. Migration scales across 30 teams, cuts onboarding from weeks to days, and delivers measurable lift in serving latency and conversion rates according to the uploader.
AI-written summary · about
chapters (8)
- 0:00ML platform challenges
- 3:14Decentralized vs centralized
- 7:30CoE template strategy
- 12:11Migration strategy
- 16:07Template design
- 21:56Scaling templates
- 23:21Summary
- 24:03Q&A
related talks
28mThe Power of Personalized Customer Experiences Through AI Innovations
39mA recommendation engine for your applications
55mBuilding a Recommendation Engine with Machine Learning Techniques
27mEnhancing Personalization Using Recommendation Systems & Multi-Armed Bandits
31mCreating recommender systems with Spark, Scala and Prediction.Io
32mResurrecting a Recommendations Platform
01h 14mBuilding a Recommendation System with a Hybrid Search From Scratch
29mThe Challenges of Building a Personalized Recommendation System in E-Commerce