Monitoring High-Performance Platforms With Machine Learning
summary
Description of how Movile’s Core Machine Learning team used simple open-source tools and off-the-shelf ML algorithms to build a monitoring system for high-performance platforms that prevented roughly $3 million in losses. Covers technology choices (open-source tools), the problem (platform monitoring to protect revenue), and the practical implementation and outcomes.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 3:45Monitoring challenges
- 7:14Spark and MLlib tools
- 14:59Data preparation
- 21:00Feature engineering
- 25:18Model training
- 31:29Alerts and notifications
- 32:34Results and lessons
- 35:01Next steps and closing
related talks
37mOptimizing AI and ML with Platform Engineering
13mHuman-in-the-Loop MLOps: Boost Model Performance by 40%
24mEmpowering High-Performance Teams with DevOps & Machine Learning
27mML Platform Journey
16mMLOps — Understanding and Fighting Model Degradation in Production
45mAutomated data analyzer using Machine Learning
39mMethodology of ML in Performance Testing (How to Find Bottlenecks Automatically)
31mUse-Case Driven ML Platforms