Why You Should Think Like an End-to-end Data Scientist, and How
summary
Built an end-to-end ML pipeline that delivers a live Donor Readiness Score to transplant center UIs, moving from R/Python/SQL prototypes to production with AWS SNS and Terraform alerts and a Connect server for monitoring. Integration work spans data, DevOps, and app teams, takes roughly a year for first pass, and succeeds: partners view scores in their systems. Troubleshooting used scraping of ~10,000 error logs across 30–40 reports to find an expired certificate causing failures.
AI-written summary · about
chapters (5)
- 0:00Introduction
- 3:18Prototype to production
- 7:12Cross-team collaboration
- 11:56End-to-end problem solving
- 17:13Key takeaways
related talks
30mGoing Full Stack with Data Science: Using Technical Readiness...
18mDesigning a scalable ML Ops Pipeline: Insights and best practices
37mA Day in the Life of a Data Scientist. Conquer ML Lifecycle on Kubernetes
39mDoing Data: The Critical Process of Data Preparation (...)
01h 03mOne Flow to Rule Them All: Building the end to end ML project to production
52mPreparing data for reporting, ML, and AI on AWS
31mProductizing Machine Learning over Big Data with AWS tools
28mBuild an End-to-End ML Workflow for Your Organization