Why you don’t want your Realtime Analytics to be Exact
summary
Mikio Braun discusses making realtime big-data analytics cheaper by accepting approximate rather than exact results. He compares the trade-offs of exact scaling-out solutions and describes approaches for trading accuracy for speed and lower cost in systems that need more recent (but not perfectly precise) analytics.
AI-written summary · about
chapters (4)
related talks
26mModern Analytics: One Size Does Not Fit All
52mLambda Architecture for Real-Time Analytics — Risks and Benefits
47mBuilding a Real-Time Analytics Database
44mNear-Real-Time Event Analytics in a High-Load Project
08mReal-Time Data Systems: Speed, Scale, and Resilience
38mRealtime Data Activation - Analytics, Intelligence & Decision Making
30mData Processing in RTB: Fast, Cheap and 98% Accurate
09mLet's Get Real: Acting on Data in Real Time