We invite proposals for KDD Cup 2013 competition. KDD Cup is the well-known data mining competition of the annual ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD-2013 conference will be held in Chicago from August 11 – 14, 2013. The competition will last between 6 and 8 weeks and the winners should be notified by end-June. The winners will be announced in the KDD-2013 conference and we are planning to run a workshop as well.
The KDD Cup start date is 4/10/13. Please register here.
Proposals should include a short paragraph on each of the following items:
- Description of the problem addressed, with general background information on the application domain.
- Description of the available data, guarantee of availability, guarantee of confidentiality of the “ground truth”, and size.
- Description of the competition tasks, their scientific and technical merit and their practical significance.
- Description of the evaluation procedures and established baselines (if possible, please provide evidence that non-trivial performance can be achieved, and an estimate of what constitutes a significant difference in performance). The evaluation metrics should be both meaningful for the application and statistically sound for objective performance comparison.
- List of the available resources (team member availability, computers, support staff, other equipment, sponsors).
- Names, affiliations, postal addresses, phone numbers, and short biographies of the organizers.
Whether you will award prizes of any form to winning teams (e.g., sponsor the conference registration, monetary reward).
A good competition task is one that is practically useful, scientifically or technically challenging, can be done without extensive application domain knowledge, and can be evaluated objectively. Of particular interests are non-traditional tasks/data that may need novel techniques and solutions and/or thoughtful feature construction.
Of particular interest this year are proposals involving data and a problem from a field or discipline, that if successfully executed, will result in a contribution of some lasting value to that field.You can assume that Kaggle will provide the technical support of running the contest. The data needs to be available no later than mid-March.
Please send your proposals to kddcup@kdd13.org by 4/1/13 or submit the information through Kaggle. If you have initial questions about the suitability of your data/problem feel free to reach out additional to kddcup@kdd13.org.