Data Innovation in a Pressure Cooker: Schiphol Data Science Hackathon
On October 28 Schiphol Airport, Microsoft, and GoDataDriven, organized the Schiphol Data Science Hackathon. Five teams of data scientists worked together on various unique data sets provided by the airport. Data included bird radar data and luggage data. At the end of this day, the teams presented several useful solutions to a jury, after which a winner was appointed.
Developing predictive models at the hackathon
Products that the teams worked on included the prediction of bird movements around the Polderbaan with a five minutes resolution. This is very valuable for the Bird Control team at Schiphol, as this increases the accuracy of predicting potential bird hazards around the airport.
Another team was able to plot luggage streams on a map of the airport, which could make it possible to detect potential clutter in an early stage, enabling the airport to avoid these situations.
Demo's to the jury at the hackathon
The jury praised the quality of the presentations. "I am impressed with the work that all the teams have done in just one day. We will definitely use all the insights to reach our goal of becoming the best digital airport", says chairman of the jury, Sjoerd Blum, head of Business Technology at Schiphol.
Erik Vlasblom, who was part of the winnning team, says: "It was phenomenal to work together as a team and to apply our machine learning knowledge to Schiphol's operations". Fellow team member Liam McMenamin adds: "This is truly a unique opportunity to access these data sets. It is quite an effort to get to grips with the data sets and to be able to come up with something useful".
For Schiphol, the next step is to continue the development of the several ideas that sprung from the hackathon. The Data Innovation Lab at Schiphol is eager to make this happen.
Follow us for more of this
Testing and debugging Apache Airflow
February 22, 2019
The Zen of Python and Apache Airflow
February 18, 2019
AWS Machine Learning Competency Status for GoDataDriven
February 14, 2019
GoDataDriven Open Source Contribution for January 2019, the Apache Edition
February 13, 2019
Our social responsibility as a company
February 08, 2019
Keras: multi-label classification with ImageDataGenerator
January 31, 2019