Keynote: DJ Patil
summary
Memo dated March 14 2020 describes a quick playbook: acquire messy tests and hospital censuses, clean and join them, and run a Johns Hopkins epidemiological model after a rapid lift and shift onto donated Amazon servers. The team builds dashboards and a Cal cat assessment tool, authors a plain data catalog/data book, and publishes nightly slide decks. Results: models guide urgent shutdown decisions but only work when paired with grounded storytelling and volunteer-derived local data.
AI-written summary · about
chapters (25)
- 0:00Welcome DJ Patil
- 1:07March 14 2020 changed everything
- 3:16California COVID memo
- 5:06First draft team assembly
- 7:15Epidemiological models to production
- 9:24Shutting down California
- 10:50CalCat tool building
- 12:16Data tied to human stories
- 13:21Data cataloging overlooked
- 15:10Models vs policy decisions
- 17:19Storytelling power in data
- 19:47First draft lists in crisis
- 21:56Models vs storytelling in health
- 23:20Data has names and stories
- 24:45Data science is teamwork
- 26:29Infusing possibility into projects
- 28:14Breaking problems daily
- 31:42Q&A changed my thinking
- 35:18Q&A COVID data quality
- 39:16Q&A what I wish I had done differently
- 44:16Q&A data science in government
- 49:16Q&A becoming a data scientist
- 51:49Q&A my biggest contribution
- 53:57Q&A open source trends
- 58:11Closing remarks
related talks
42mVisualizing COVID-19 Data
43mKeynote
07mNew York City weathers pandemic with data-first response
27mBeyond a Machine Learning Model
29mHow data science shortened the COVID-19 pandemic by 2 months
36mKeynote: Data, Decision Making, and Being Human
34mML and analytics addressing nationwide COVID-19 impact and recovery
22mCOVID-19: Data Science & Expertise