Modernizing Your Data Strategy With Machine Learning & The Cloud
summary
Accell Group uses Tamr to harmonize product and supplier master data, ingesting roughly 400,000 records and scaling to millions, training a recall-focused ML model within weeks and reaching a production milestone in about nine months. The pipeline deduplicates ~200-component e-bikes, achieves reported recall in the mid‑90s (model validation near 99), raises tracked data quality from ~50–60% to ~91%, and feeds daily ERP syncs plus a data warehouse with governance and SME feedback loops.
AI-written summary · about
chapters (13)
- 0:00Introduction and speakers
- 1:03Excel Group background
- 2:47Data challenges at Excel Group
- 6:17Why machine learning was key
- 8:43Expanding data initiatives
- 10:48Impact on downstream applications
- 12:35Future plans and operational benefits
- 13:38Advice for overcoming challenges
- 16:09Q&A: Implementation timeline
- 19:04Q&A: Cultural mindset shift
- 20:32Q&A: Technical ML details
- 22:00Q&A: Data quality assessment
- 24:52Closing and next steps
related talks
37mData Mastering at Scale with AI
22mScaling analytics and AI: It's mostly about culture
33mLeaning into the Data Mesh
28mApplied ML at Scale Strategies & Insights
28mAccelerating AI at Scale with Data
32mMaking Models Work: How an optimized ML lifecycle can drive better ROI
19mDrive transformation through machine learning
27mHow to make ML teams 80% more productive.