For our next event, we have joined forces with KLM to share results and learnings of a full-cycle data science project on passenger forecasting. A must-attend event for anyone working in the field of applied data science!
-- Background:
Nobody likes throwing good food away, while everybody likes to get a fresh meal on a long-distance flight. In to order take just the right amount of meals on board, KLM successfully executed a project to improve their forecast of the number of passengers on-board every flight. This meetup, we will walk you through the entire process and share the challenges of going from a rough idea to an industrialised data science solution.
-- Agenda:
17.45 - Doors open
18.00 - Drinks & snacks
18.30 - Welcome
18.45 - The project: meals on board
19.00 - The science: forecasting airline passengers
** 15 min break **
20.00 - The engineering: bringing it to production
20.30 - Wrap-up and time for social drinks, doors close at 21.00
-- The project: meals on board
Joyce Morren, Project Manager Supply Chain at KLM, will outline the project: the idea, detailed use case, team, phases and the final data science product. In addition, she will share some of the key results and learnings of the project.
-- The science: forecasting airline passengers
Alexander Backus, Lead Data Scientist at BigData Republic, will talk data science: framing the modeling problem, performance metrics, validation strategy, machine-learning algorithms and challenges from a data science perspective.
-- The engineering: serving forecasts in production
Daan Debie, Director Engineering & Architecture at KLM, will map the road to production of this project: solution architecture, data platform (Spark, HBase, Docker), microservices, model serving, monitoring and challenges from a data engineering perspective.