Data science demystified
summary
Claims that 2023 produces 120 zettabytes a year and that value comes from turning raw streams into decisions via a concrete pipeline: fetch, wrangle, explore, feature‑engineer, model, validate and tell a story. Shows tools like Python and Spark, gives a quirky working example—the dog‑or‑muffin model—and practical practices that actually get adopted: data contracts, vendor APIs, governance, premortems and continual fairness checks rather than vague assertions about “data science.”
AI-written summary · about
chapters (9)
- 0:00Data science importance
- 1:27What is data science
- 3:38Data types and cleaning
- 5:04Model building techniques
- 7:12Machine learning models
- 8:57Data storytelling
- 10:06Ethics in data science
- 12:34Data science for engineers
- 13:59Best practices
related talks
41mData Science – The New Troublemaker in the Delivery Pipeline
34mData Science beasts (failures) and where to find them
40mBridging bytes and behavior with Data Science and UX Research
47mA Practical(ish) Introduction to Data Science
29mData Science Best Practices : From Proof of Concepts to Production
34mPast The Hype: A Better Way To Think About Big Data
37mLife of a data scientist
24mWhat the...? Data Science Questions Asked and Answered