In addition to our three exciting challenges, we have prepared a very innovative ECML-PKDD 2016 discovery challenge, which collocates in the realm of Automatic Network Management.
This challenge is one of the first explorations of ML for automatic network analysis. Our goal is to promote the use of ML for network-related tasks in general and, at the same time, to assess the participants' ability to quickly build a learning-based system showing a reliable performance.
Sept. 7: test data released, submission page opens
Sept. 10: submissions due
Sept. 12: Results and Paper invitations
Sept. 23: ECML-PKDD challenge track
The schedule is tight but we have encoded the network data using simple feature vectors for learning a multi-class, single label, classification task. Thus, you can simply try your own multiclass classification algorithms and watch if they improve on strong baselines.
The aim is to find out which ML algorithms can better deal with this kind of data.