Machine Learning Contest

New Contest at



Discovery Challenge Overview

Organization | Overview | Task and DatasetsTimeline


General description: tasks and dataset is a free and open access multimedia repository of video lectures, mainly of research and educational character. The lectures are given by distinguished scholars and scientists at the most important and prominent events like conferences, summer schools, workshops and science promotional events from many fields of Science. The portal is aimed at promoting science, exchanging ideas and fostering knowledge sharing by providing high quality didactic contents not only to the scientific community but also to the general public. All lectures, accompanying documents, information and links are systematically selected and classified through the editorial process taking into account also users’ comments.

The ECML-PKDD 2011 Discovery Challenge is organized in order to improve the website’s current recommender system. The challenge consists of two main tasks and a “side-by” contest. The provided data is for both of the tasks, and it is up to the contestants how it will be used for learning (building up) a recommender.

Due to the nature of the problem, each of the tasks has its own merit: task 1 simulates new-user and new- item recommendation (cold-start mode), task 2 simulates clickstream based recommendation (normal mode).

Data from VL.Net site does not include any explicit nor implicit user profiles. Due to the privacy- preserving constraints implicit profiles embodied in viewing sequences (clickstreams) have been transformed, so that no individual viewing sequence information can be revealed or reconstructed. There are however other viewing related data included: i) co-viewing frequencies ii) pooled viewing sequences, and iii) content related information available: lecture category taxonomy, names, descriptions and slide titles (where available), authors, institutions, lecture events and timestamps.

More details about the tasks and the dataset are available from




The prizes of this year’s Discovery Challenge are sponsored by the EU FP7 Project e-LICO ( The prizes for each of the tasks are:

  • 1st place: 1500€
  • 2nd place: 700€
  • 3rd place: 300€



Also new prizes by Rapid Miner,com_myblog/show,New-Contest-Euro-5500-Price-Money-and-Free-Trip-to-RCOMM-2012.html/Itemid,172/

The contest consists of two recommender system problem tasks and a side-by workflow contest in which Rapid-I sponsors the best RapidMiner workflow with an free admission to RCOMM 2012 including flight and hotel.


 ECML/PKDD Challenge
The total award of the challenge sums to Euro 5500 – plus the free trip to the RCOMM 2012!
All details on the challenge can be found at

We are looking forward to your RapidMiner workflows.


ChallengesVideoLectures.Net Recommender System Challenge/Workflow contest

Status Open
Type Scientific
Start 2011-04-18 10:00:00 CET
End 2011-07-08 23:59:59 CET
Prize 5,500€
Registration is required.
In addition to the recommendation tasks, challenge contestants will be encouraged to compete with their computational solutions, i.e. computational workflows.
Workflows will be judged by the expert panel assembled by the organizers, taking into account not only the performance on the tasks, but also other criteria (e.g. understandability, efficiency). 

The submission for the workflow contest is scheduled after closing the challenge (8th July). Details about submission and evaluation will be given in due time before closing of the challenge.
The best workflow submission will be awarded 500€. Authors of the best RapidMiner workflow will have free admission to the RapidMiner Community Meeting and Conference – RCOMM 2012.

Note: Some basic workflows (constructed in RapidMiner) that can be useful in developing the solutions for the challenge tracks are available on myExperiment portal, as e-LICO recommender workflows.




Author: Ajay Ohri

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: