Building Successful Data Science Projects
summary
Clear specifics decide whether to watch: is there a written specification and de‑risking plan, and does the $1 million client claim trace to measurable outcomes; which tools and diagnostics are actually used — scikit-learn random forest SHAP SQL — and is a baseline or mean regressor evaluated first; how deployment is planned and tested; whether surprising numbers show up (one‑in‑1000 VC hit rates, small teams growing 10 to 25, duplicated invoices found by simple counts) and whether a working pipeline ends up deployed.
AI-written summary · about
chapters (5)
- 0:00Start
- 6:01Story Automated price comparison
- 10:08Solution write a specification
- 15:16Data Maturity Model
- 16:53Story insurance & low client trust
related talks
28mData Science Project Patterns that Work
54mThe secret sauce of data science management
37mBridging the gap: from Data Science to service
31mWhy Most Data Projects Fail and How to Avoid It
54mFrom the Life of a Data Scientist
46mPanel Discussion: Business Side of Data Science
33mManaging Stakeholders: The Key to Successful Data Science for Business
35mApplied Data Science