Analytics for S7 Aircraft: Pets vs Cattle
summary
An S7 Airlines engineering talk about aviation analytics contrasts treating aircraft as "pets" versus "cattle": it describes building operational analytics for maintenance schedules, frequent inspections, and delay-penalty risks using concrete data engineering and monitoring approaches rather than fast-moving A/B-test style development. Technologies and exact tools are not named in the abstract, but the focus is on analytics systems to support strict regulatory maintenance cycles and minimize costly delays.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:12S7 and airline data
- 7:58Aircraft maintenance
- 12:10Pets vs Cattle problem
- 17:32Data Science methodology
- 19:40Data preparation for model
- 23:12Data cleaning and features
- 27:47Modeling and evaluation
- 30:39Results and model deployment
- 31:43Transparency requirements
- 32:45Engineer collaboration
- 33:48Q&A
related talks
40mML in Production: Why Analysts and Backend Struggle to Agree
38mData Secrets from a Platform Engineer
42mArchitecting for Reliability
30mEnterprise AI: How To Operationalize Data Analytics At Scale
31mElevating DevOps with Integrating Analytics into CI/CD Pipelines
41mReal Time Architectures Real Fast
32mEscalating complexity: DevOps learnings from Air France 447
24mAIOps, are we there yet?