Using Data Riches: A Tale of two projects
summary
Two applied projects show what data riches actually deliver: a semiconductor failure‑analysis system that builds an ontology and indexed retrieval layer and reduced discovery from 3–4 weeks to under a day, cutting repeat tests that cost $100k each while a failed batch chips $5M; and a public‑health pipeline that aggregates surveillance feeds into an agent‑based Repast SEIAR model for vaccine allocation that the state reports as saving over $50M and both lives and money.
AI-written summary · about
chapters (24)
- 0:00Introduction
- 3:07Disruptive innovation
- 3:29Hurdle race
- 5:27Big data
- 6:48Data
- 8:29Data Generation
- 9:35Why Focus on Data
- 10:22How to Balance Data and Opinion
- 11:33The Nexus of Data Science
- 13:42Singularity
- 14:55AI
- 15:38Data sizes
- 16:29Law of large numbers
- 17:42Volume of data
- 20:06Types of data
- 21:22Two projects
- 22:34fafi
- 23:37failure analysis
- 24:19data collection
- 26:23business cards
- 27:37Ontology
- 28:45Public Health
- 33:20Magic
- 34:55Questions
related talks
38mThe Real World of Data Analytics
01h 02mMaking Data Great Again
50mInnovation and data analytics: Solving real-world challenges
38mReal world data & analytics journeys
47mData for good: Lessons from the frontline
28mGenerate Insights, Not Excuses: How your data is slowing you down
47mData Analytics: Realizing the Full Potential
26mData with a mission: a COVID-19 API case study