AWS On Air ft. BMW & BCG
summary
Machine learning model predicts future take rates for BMW options three to four years out, producing market‑ and model‑level percentages used to size supplier orders. System goes live in six months, hands over to a devops team, and replaces much of the manual market-by-market planning. Architecture uses API Gateway to trigger Lambda inference, Glue for ETL and automated data quality checks, and a Tableau dashboard for model selection and accuracy monitoring.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 0:33The Business Problem
- 2:54Developing the Solution
- 6:12Collaboration and Launch
- 7:28Technical Architecture
- 9:35Future Outlook
related talks
36mHow BMW stays on the fast track by building the Connected AI Platform for digital products
12mAI-Powered Predictive Analytics for Multi-Cloud Management
30mAI in Retail - Advancing Promo Demand Forecasting
01h 05mAzure Machine Learning for the Developer
57mTaking Models to the Next Level with Azure Machine Learning
16mTransforming Inventory Forecasting with Production ML
19mDrive transformation through machine learning
27mBuild Intelligent Business Applications with Machine Learning and Cloud Foundry