Chemnitz, 22.06.2011: Students from Dortmund TU and the Karlsruhe Institute of Technology competed against participants from 20 countries and achieved the top two spaces in the DATA-MINING-CUP 2011 - the world's largest data mining competition. For the first time in the history of the DATA-MINING-CUP the participants had to solve two different problems.
The competition was to create Recommendation algorithms with maximum prediction quality
The first task involves statically analysing an algorithm i.e. training the algorithm to historical transaction data, the training data. In order to be able to evaluate the prediction quality of the recommendations, the first transactions are specified on a test quantity for each session. These are the test data. The objective of the algorithm is to predict the remaining transaction data for the session. The generated prediction file is sent to the prudsys DMC team. The predicted products are then compared against the actual remaining transaction data from the sessions, the evaluation data. The team with the highest score based on the evaluation data wins.
The second task involves dynamically evaluating an algorithm, the implementation of which is sent to the prudsys DMC team. The objective is to apply the algorithm step-by-step to historical transaction data and continuously predict the next products in a session. As it receives all the transactions from each session one after the other in succession, it learns and predicts at the same time. The team with the highest score over all prediction steps wins.
The first two places were taken by students at Dortmund TU and the Karlsruhe Institute of Technology. With teams from the University of San Diego (USA), Aristotle University of Thessaloniki (Greece) and Amirkabir University of Technology (Iran) there were also several international teams on the top ten list this year.
More about the DATA-MINING-CUP 2011, which has now come to an end, and the DATA-MINING-CUP 2012 at: