Backstage interview
summary
Walks through an applied causal-inference pipeline for a manufacturing line: data collection from sensors, building a causal graph from expert knowledge, and running the open-source do package to move beyond correlation. Shows how variables tied to glass pool production are identified as actual drivers of quality, explains handling messy biased sensor data, and reports whether the causal analysis highlights actionable interventions that change defect rates.
AI-written summary · about
related talks
06mCausal Machine Learning – What’s in it for Data Scientists?
01h 12mIntroduction to Causal Inference
31mIntroduction to Causal Inference using pgmpy
21mHow Data Science Complements the Six Sigma Methodology in Manufacturing
37mEngineering data quality
24mAn introduction to Causal Inference with Python – making accurate estimates of cause and effect from
11mBig Data Moonshots and Ground Control
08mdata science in automotive