Data Processing at Blue Yonder
• November 2, 2020
Florian Jetter, Sr Data Scientist at Blue Yonder, joins Hugo Bowne-Anderson and James Bourbeau to discuss supply chain analytics at scale.
Blue Yonder provides software-as-a-service products around supply chain management. Along such a supply chain there are billions of billions of decisions to be made, how much to order, when to ship products, how much stock to keep in distribution centers, and so on.
Blue Yonder automates more and more of those decisions using machine learning and optimization. They are heavily using Python and Dask for processing the data-intensive workloads.
This live stream will follow such a „data supply chain“ from beginning to end, from ingesting the customer data to the delivery of massive amounts of automated decisions to the customer.
You will learn how Dask helps us to extract the data, transform it for a machine learning application, and load the results back into a persistence layer. Sounds trivial? It is to some extent!
At Blue Yonder, they learnt it the hard way: The hardest problems to solve are not how to build the most sophisticated models. It is how to get the „data supply chain“ robust, secure, scalable, customizable, and not to forget: cheap!
After attending, you’ll know
- That buying milk at your local supermarket is a highly non-trivial process,
- How to incorporate a relational database into your data pipeline,
- How to build a ML data pipeline at terabyte scale using parquet, dask, and kartotek,
- And finally, how to join data at scale without breaking a sweat (kind of).
Join us this Thursday, November 5th at 1 pm Central European Time (UTC+1) by signing up here and dive into the wonderful world of scalable supply chain analytics (note the time is different this week, as our guests are in Europe)!