Shorten the Path to Production with In-Database Machine Learning
summary
Claims are concrete: Nimble Storage builds Infosight with in-database ML and HPE acquires it after 3× engineer productivity and 86% of cases auto-resolved; Phillips runs predictive maintenance on MRI components from years of device logs; Jaguar moves telemetry into Vertica and credits database ML with race wins (Mitch Evans, Sam Bird) after switching storage/ML stack; users report shrinking clusters—examples include moving workloads from 278 Spark nodes to 9 nodes—and models train and serve without reimplementing pipelines.
AI-written summary · about
chapters (9)
- 0:00Introduction to in-database machine learning
- 3:20ML success case study
- 12:11Why ML projects fail
- 17:48Databases for modern data
- 24:15Benefits of in-database ML
- 29:44ML workflow in databases
- 35:48Q&A on reproducibility
- 41:55Data Lake integration
- 44:03Optimizing data science
related talks
12mRevolutionizing Data Management
32mMaking Models Work: How an optimized ML lifecycle can drive better ROI
19mSustaining ML in the enterprise
10mAutomation of decisions to augment efficiency in the enterprise
34mScaling ML in the Traditional Enterprise
40mIn-Database Machine Learning with Jupyter
31mIn-database machine learning: Automate, scale, deploy
21mHow The Application Of Machine Learning Is Changing The Way Companies Use Data