1st International Workshop on AI Methods in Data Mining Challenges (DMGATE'18)
Poznań, Poland, 9 - 12 September, 2018
AAIA'18 Data Mining Competition Knowledge Pit
The scope of DMGATE is to establish a forum for data scientists working at the edge of academic research and commercial applications, keen on developing and using AI-based methods in data mining projects and challenges. DMGATE continues the tradition of data mining competitions organized at FedCSIS.
This year’s competition starts on April 3 and lasts until May 7. The task is to predict win-rates of Hearthstone decks used by players with various skill and experience. Details are available here.
As usual, competition winners will be granted with financial awards and/or free conference registration. Moreover, we will invite a small group of authors of the most interesting competition solutions to submit papers that will be reviewed on special fast-track basis.
Starting from this year, we also welcome regular paper submissions describing new approaches for analyzing data sets published online during previous competitions. These papers will be peer-reviewed by top specialists in the area of data science and – if accepted – they will be presented at the DMGATE session together with the papers prepared by this year’s competition winners.
We believe that it is highly important for the data science community to keep up the discussion on both current and past data mining competitions, in order to jointly develop a firm knowledge base on how to apply AI-based data mining methods in real life.
WINNERS
- Quang Hieu Vu, ZALORA, and Dymitr Ruta, EBTIC, Khalifa University, United Arab Emirates: Predicting Win-rates of Hearthstone Decks: Models and Features that Won AAIA’2018 Data Mining Challenge
- Ling Cen, EBTIC, Khalifa University, United Arab Emirates, and Andrzej Ruta, ING Bank Slaski, Poland
- Jan Jakubik, Wrocław University of Science and Technology, Poland: A Neural Network Approach to Hearthstone Win Rate Prediction
Congratulation on your excellent results! We would also like to distinguish two more teams:
- Micha Kuźba and Ryszard Poklewski-Koziełł
- Adam Witkowski, Jan Betley, and Anna Sztyber
Related papers available in the Proceedings of FedCSIS 2018.
Paper submission
- Authors should submit draft papers (as Postscript, PDF or MSWord file).
- The total length of a paper should not exceed 10 pages IEEE style (including tables, figures and references). IEEE style templates are available here.
- Papers will be refereed and accepted on the basis of their scientific merit and relevance to the workshop.
- Preprints containing accepted papers will be published on a USB memory stick provided to the FedCSIS participants.
- Only papers presented at the conference will be published in Conference Proceedings and submitted for inclusion in the IEEE Xplore® database.
- Conference proceedings will be published in a volume with ISBN, ISSN and DOI numbers and posted at the conference WWW site.
- Conference proceedings will be indexed in BazEkon and submitted for indexation in: Thomson Reuters - Conference Proceedings Citation Index, SciVerse Scopus, Inspec, Index Copernicus, DBLP Computer Science Bibliography and Google Scholar
- Extended versions of selected papers presented during the conference will be published as Special Issue(s).
- Organizers reserve right to move accepted papers between FedCSIS events.