is designing ML solutions to deliver human capital insights
summary
ADP turns 90 million anonymized employee records into production ML: a skills graph stored in Amazon Neptune, 20 SageMaker-hosted models, and APIs that hit tens of milliseconds with five nines availability. Moving to AWS cuts model deployment from two weeks to one day, runs seven teams reusing features, and supports 3 PB of data and 400 TB/day streaming. Job-title collapse goes from 21 million raw titles to 9,000 standardized roles and drives compensation and turnover models in production.
AI-written summary · about
chapters (8)
- 0:00Introduction and ADP overview
- 3:51Data processing and anonymization
- 7:10Key ML-driven products and use cases
- 15:46Skills graph and organizational benchmarks
- 20:12Moving ML to AWS SageMaker
- 23:08Cloud migration during COVID
- 26:51ML operations and deployment speed
- 29:22Future challenges and closing
related talks
52mPreparing data for reporting, ML, and AI on AWS
14mMLOps at Scale: AI Systems for HR Transformation
31mUse AutoML to create high-quality models with just a few clicks
44mA generative AI–enabled enterprise: Transformative AI/ML on AWS
31mAccelerating AI with Hyperscaler Platforms
40mReady, set, data: Perfecting the art of talent matching with AI
32mBuild quality ML models easily & quickly with Amazon SageMaker Autopilot
29mSolve common business problems with AI and ML