Data Driven Production Process Optimization Machine Learning Toolbox & Beverage Industry
summary
A modular DaPro toolbox built on RapidMiner with industry-specific data schemas and semi-automated data mapping enables brewers and process engineers to run guided analyses and AutoML without coding. Malt-yield models hit a 0.6% relative error on mixed-malt batches and deploy as dashboards and simulators to pick mixtures; broader rollouts expect ~20% efficiency gain. Energy use cases target compressor peak avoidance via short-term forecasting. Delivered components: schema-driven connectors, validation assistant, auto model pipelines and deployable prediction services (RapidMiner AutoML, DaPro modular toolbox).
AI-written summary · about
chapters (11)
- 0:00Introduction and speaker
- 0:31RapidMiner company overview
- 1:53Project goals and challenges
- 3:57Machine learning toolbox
- 5:06Process optimization use cases
- 7:16Use case implementation
- 10:45Advanced data mining approach
- 13:46Toolbox features and integration
- 16:44Deployment and visualization
- 19:05Key takeaways and learnings
- 20:48Q&A session
related talks
32mAutomating Production Production Level Machine Learning on AWS
14mGetting Machine Learning applications into production using MLOps and CD4ML
27mA Look Inside Applied Machine Learning
24mSmart approach in development and deployment process for ML models
28mHow to boost data science routines with DataArt’s AutoML Platform?
37mBig Data Analytics, Machine Learning, Real Time Processing
15mBig Data, Artificial Intelligence, Machine Learning
39mDoing Data: The Critical Process of Data Preparation (...)